{
  "documentationLink": "https://cloud.google.com/video-intelligence/docs/",
  "parameters": {
    "upload_protocol": {
      "description": "Upload protocol for media (e.g. \"raw\", \"multipart\").",
      "type": "string",
      "location": "query"
    },
    "alt": {
      "enumDescriptions": [
        "Responses with Content-Type of application/json",
        "Media download with context-dependent Content-Type",
        "Responses with Content-Type of application/x-protobuf"
      ],
      "location": "query",
      "description": "Data format for response.",
      "default": "json",
      "type": "string",
      "enum": [
        "json",
        "media",
        "proto"
      ]
    },
    "$.xgafv": {
      "enumDescriptions": [
        "v1 error format",
        "v2 error format"
      ],
      "location": "query",
      "description": "V1 error format.",
      "type": "string",
      "enum": [
        "1",
        "2"
      ]
    },
    "prettyPrint": {
      "type": "boolean",
      "description": "Returns response with indentations and line breaks.",
      "default": "true",
      "location": "query"
    },
    "uploadType": {
      "location": "query",
      "description": "Legacy upload protocol for media (e.g. \"media\", \"multipart\").",
      "type": "string"
    },
    "fields": {
      "description": "Selector specifying which fields to include in a partial response.",
      "type": "string",
      "location": "query"
    },
    "access_token": {
      "location": "query",
      "type": "string",
      "description": "OAuth access token."
    },
    "key": {
      "description": "API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.",
      "location": "query",
      "type": "string"
    },
    "quotaUser": {
      "location": "query",
      "description": "Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.",
      "type": "string"
    },
    "callback": {
      "description": "JSONP",
      "location": "query",
      "type": "string"
    },
    "oauth_token": {
      "type": "string",
      "description": "OAuth 2.0 token for the current user.",
      "location": "query"
    }
  },
  "batchPath": "batch",
  "revision": "20261106",
  "rootUrl": "https://videointelligence.googleapis.com/",
  "discoveryVersion": "v1",
  "version_module": true,
  "schemas": {
    "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject",
      "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.",
      "properties": {
        "landmarks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark"
          },
          "description": "Optional. The detected landmarks.",
          "type": "array"
        },
        "timeOffset": {
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.",
          "format": "google-duration",
          "type": "string"
        },
        "attributes": {
          "description": "Optional. The attributes of the object in the bounding box.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute"
          }
        },
        "normalizedBoundingBox": {
          "description": "Normalized Bounding box in a frame, where the object is located.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_WordInfo": {
      "properties": {
        "startTime": {
          "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.",
          "format": "google-duration",
          "type": "string"
        },
        "speakerTag": {
          "type": "integer",
          "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.",
          "readOnly": true,
          "format": "int32"
        },
        "endTime": {
          "type": "string",
          "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.",
          "format": "google-duration"
        },
        "confidence": {
          "format": "float",
          "readOnly": true,
          "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.",
          "type": "number"
        },
        "speakerLabel": {
          "type": "string",
          "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.",
          "readOnly": true
        },
        "word": {
          "type": "string",
          "description": "The word corresponding to this set of information."
        }
      },
      "type": "object",
      "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.",
      "id": "GoogleCloudVideointelligenceV1p1beta1_WordInfo"
    },
    "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription": {
      "description": "A speech recognition result corresponding to a portion of the audio.",
      "type": "object",
      "properties": {
        "alternatives": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative"
          },
          "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.",
          "type": "array"
        },
        "languageCode": {
          "readOnly": true,
          "type": "string",
          "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription"
    },
    "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus": {
      "id": "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus",
      "description": "Status of exporting annotation response to user specified `output_uri`.",
      "type": "object",
      "properties": {
        "state": {
          "enumDescriptions": [
            "Default value.",
            "Export succeeded.",
            "Export failed."
          ],
          "type": "string",
          "enum": [
            "STATE_UNSPECIFIED",
            "SUCCEEDED",
            "FAILED"
          ],
          "description": "Output only. State of the `output_uri` export.",
          "readOnly": true
        },
        "status": {
          "readOnly": true,
          "$ref": "GoogleRpc_Status",
          "description": "Output only. Only set if state is FAILED."
        }
      }
    },
    "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly": {
      "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.",
      "id": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly",
      "type": "object",
      "properties": {
        "vertices": {
          "description": "Normalized vertices of the bounding polygon.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex"
          }
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_WordInfo": {
      "properties": {
        "speakerLabel": {
          "readOnly": true,
          "type": "string",
          "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word."
        },
        "startTime": {
          "format": "google-duration",
          "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.",
          "type": "string"
        },
        "speakerTag": {
          "type": "integer",
          "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.",
          "format": "int32",
          "readOnly": true
        },
        "endTime": {
          "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.",
          "format": "google-duration",
          "type": "string"
        },
        "word": {
          "description": "The word corresponding to this set of information.",
          "type": "string"
        },
        "confidence": {
          "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.",
          "type": "number",
          "readOnly": true,
          "format": "float"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p3beta1_WordInfo",
      "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation": {
      "type": "object",
      "description": "Deprecated. No effect.",
      "id": "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation",
      "deprecated": true,
      "properties": {
        "frames": {
          "description": "All video frames where a face was detected.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceFrame"
          }
        },
        "thumbnail": {
          "description": "Thumbnail of a representative face view (in JPEG format).",
          "format": "byte",
          "type": "string"
        },
        "segments": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceSegment"
          },
          "description": "All video segments where a face was detected.",
          "type": "array"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_TextSegment": {
      "type": "object",
      "properties": {
        "segment": {
          "description": "Video segment where a text snippet was detected.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment"
        },
        "frames": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextFrame"
          },
          "type": "array",
          "description": "Information related to the frames where OCR detected text appears."
        },
        "confidence": {
          "format": "float",
          "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.",
          "type": "number"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_TextSegment",
      "description": "Video segment level annotation results for text detection."
    },
    "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionConfig": {
      "properties": {
        "model": {
          "type": "string",
          "description": "Model to use for face detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\"."
        },
        "includeAttributes": {
          "description": "Whether to enable face attributes detection, such as glasses, dark_glasses, mouth_open etc. Ignored if 'include_bounding_boxes' is set to false.",
          "type": "boolean"
        },
        "includeBoundingBoxes": {
          "type": "boolean",
          "description": "Whether bounding boxes are included in the face annotation output."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionConfig",
      "description": "Config for FACE_DETECTION.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1beta2_SpeechTranscription": {
      "properties": {
        "alternatives": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative"
          },
          "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer."
        },
        "languageCode": {
          "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.",
          "readOnly": true,
          "type": "string"
        }
      },
      "id": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription",
      "description": "A speech recognition result corresponding to a portion of the audio.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1beta2_DetectedLandmark": {
      "properties": {
        "confidence": {
          "description": "The confidence score of the detected landmark. Range [0, 1].",
          "format": "float",
          "type": "number"
        },
        "name": {
          "description": "The name of this landmark, for example, left_hand, right_shoulder.",
          "type": "string"
        },
        "point": {
          "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex"
        }
      },
      "description": "A generic detected landmark represented by name in string format and a 2D location.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_DetectedLandmark"
    },
    "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress": {
      "properties": {
        "progressPercent": {
          "type": "integer",
          "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.",
          "format": "int32"
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment",
          "description": "Specifies which segment is being tracked if the request contains more than one segment."
        },
        "inputUri": {
          "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).",
          "type": "string"
        },
        "updateTime": {
          "description": "Time of the most recent update.",
          "format": "google-datetime",
          "type": "string"
        },
        "startTime": {
          "description": "Time when the request was received.",
          "type": "string",
          "format": "google-datetime"
        },
        "exportStatus": {
          "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_ExportToOutputUriStatus"
        },
        "feature": {
          "enumDescriptions": [
            "Unspecified.",
            "Label detection. Detect objects, such as dog or flower.",
            "Shot change detection.",
            "Explicit content detection.",
            "Human face detection.",
            "Speech transcription.",
            "OCR text detection and tracking.",
            "Object detection and tracking.",
            "Logo detection, tracking, and recognition.",
            "Person detection."
          ],
          "type": "string",
          "enum": [
            "FEATURE_UNSPECIFIED",
            "LABEL_DETECTION",
            "SHOT_CHANGE_DETECTION",
            "EXPLICIT_CONTENT_DETECTION",
            "FACE_DETECTION",
            "SPEECH_TRANSCRIPTION",
            "TEXT_DETECTION",
            "OBJECT_TRACKING",
            "LOGO_RECOGNITION",
            "PERSON_DETECTION"
          ],
          "description": "Specifies which feature is being tracked if the request contains more than one feature."
        }
      },
      "id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress",
      "type": "object",
      "description": "Annotation progress for a single video."
    },
    "GoogleCloudVideointelligenceV1p3beta1_StreamingAnnotateVideoResponse": {
      "description": "`StreamingAnnotateVideoResponse` is the only message returned to the client by `StreamingAnnotateVideo`. A series of zero or more `StreamingAnnotateVideoResponse` messages are streamed back to the client.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_StreamingAnnotateVideoResponse",
      "properties": {
        "error": {
          "description": "If set, returns a google.rpc.Status message that specifies the error for the operation.",
          "$ref": "GoogleRpc_Status"
        },
        "annotationResults": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults",
          "description": "Streaming annotation results."
        },
        "annotationResultsUri": {
          "description": "Google Cloud Storage URI that stores annotation results of one streaming session in JSON format. It is the annotation_result_storage_directory from the request followed by '/cloud_project_number-session_id'.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_VideoContext": {
      "type": "object",
      "properties": {
        "segments": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment"
          },
          "type": "array",
          "description": "Video segments to annotate. The segments may overlap and are not required to be contiguous or span the whole video. If unspecified, each video is treated as a single segment."
        },
        "explicitContentDetectionConfig": {
          "description": "Config for EXPLICIT_CONTENT_DETECTION.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentDetectionConfig"
        },
        "shotChangeDetectionConfig": {
          "description": "Config for SHOT_CHANGE_DETECTION.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_ShotChangeDetectionConfig"
        },
        "textDetectionConfig": {
          "description": "Config for TEXT_DETECTION.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextDetectionConfig"
        },
        "labelDetectionConfig": {
          "description": "Config for LABEL_DETECTION.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelDetectionConfig"
        },
        "speechTranscriptionConfig": {
          "description": "Config for SPEECH_TRANSCRIPTION.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscriptionConfig"
        },
        "objectTrackingConfig": {
          "description": "Config for OBJECT_TRACKING.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingConfig"
        },
        "faceDetectionConfig": {
          "description": "Config for FACE_DETECTION.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionConfig"
        },
        "personDetectionConfig": {
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionConfig",
          "description": "Config for PERSON_DETECTION."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_VideoContext",
      "description": "Video context and/or feature-specific parameters."
    },
    "GoogleCloudVideointelligenceV1_TextSegment": {
      "id": "GoogleCloudVideointelligenceV1_TextSegment",
      "description": "Video segment level annotation results for text detection.",
      "type": "object",
      "properties": {
        "confidence": {
          "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.",
          "type": "number",
          "format": "float"
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1_VideoSegment",
          "description": "Video segment where a text snippet was detected."
        },
        "frames": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_TextFrame"
          },
          "description": "Information related to the frames where OCR detected text appears."
        }
      }
    },
    "GoogleRpc_Status": {
      "description": "The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors).",
      "type": "object",
      "id": "GoogleRpc_Status",
      "properties": {
        "details": {
          "type": "array",
          "description": "A list of messages that carry the error details. There is a common set of message types for APIs to use.",
          "items": {
            "additionalProperties": {
              "type": "any",
              "description": "Properties of the object. Contains field @type with type URL."
            },
            "type": "object"
          }
        },
        "code": {
          "format": "int32",
          "description": "The status code, which should be an enum value of google.rpc.Code.",
          "type": "integer"
        },
        "message": {
          "description": "A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1_ObjectTrackingFrame": {
      "type": "object",
      "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.",
      "id": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame",
      "properties": {
        "normalizedBoundingBox": {
          "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox",
          "description": "The normalized bounding box location of this object track for the frame."
        },
        "timeOffset": {
          "type": "string",
          "description": "The timestamp of the frame in microseconds.",
          "format": "google-duration"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_VideoSegment": {
      "description": "Video segment.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment",
      "properties": {
        "startTimeOffset": {
          "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).",
          "type": "string",
          "format": "google-duration"
        },
        "endTimeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive)."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus": {
      "id": "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus",
      "properties": {
        "state": {
          "description": "Output only. State of the `output_uri` export.",
          "readOnly": true,
          "enumDescriptions": [
            "Default value.",
            "Export succeeded.",
            "Export failed."
          ],
          "type": "string",
          "enum": [
            "STATE_UNSPECIFIED",
            "SUCCEEDED",
            "FAILED"
          ]
        },
        "status": {
          "$ref": "GoogleRpc_Status",
          "readOnly": true,
          "description": "Output only. Only set if state is FAILED."
        }
      },
      "description": "Status of exporting annotation response to user specified `output_uri`.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p2beta1_TextFrame": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_TextFrame",
      "type": "object",
      "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.",
      "properties": {
        "rotatedBoundingBox": {
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly",
          "description": "Bounding polygon of the detected text for this frame."
        },
        "timeOffset": {
          "format": "google-duration",
          "description": "Timestamp of this frame.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoRequest": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoRequest",
      "description": "Video annotation request.",
      "type": "object",
      "properties": {
        "features": {
          "type": "array",
          "items": {
            "type": "string",
            "enum": [
              "FEATURE_UNSPECIFIED",
              "LABEL_DETECTION",
              "SHOT_CHANGE_DETECTION",
              "EXPLICIT_CONTENT_DETECTION",
              "FACE_DETECTION",
              "SPEECH_TRANSCRIPTION",
              "TEXT_DETECTION",
              "OBJECT_TRACKING",
              "LOGO_RECOGNITION",
              "PERSON_DETECTION"
            ],
            "enumDescriptions": [
              "Unspecified.",
              "Label detection. Detect objects, such as dog or flower.",
              "Shot change detection.",
              "Explicit content detection.",
              "Human face detection.",
              "Speech transcription.",
              "OCR text detection and tracking.",
              "Object detection and tracking.",
              "Logo detection, tracking, and recognition.",
              "Person detection."
            ]
          },
          "description": "Required. Requested video annotation features."
        },
        "inputContent": {
          "description": "The video data bytes. If unset, the input video(s) should be specified via the `input_uri`. If set, `input_uri` must be unset.",
          "format": "byte",
          "type": "string"
        },
        "videoContext": {
          "description": "Additional video context and/or feature-specific parameters.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoContext"
        },
        "outputUri": {
          "type": "string",
          "description": "Optional. Location where the output (in JSON format) should be stored. Currently, only [Cloud Storage](https://cloud.google.com/storage/) URIs are supported. These must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/request-endpoints)."
        },
        "inputUri": {
          "description": "Input video location. Currently, only [Cloud Storage](https://cloud.google.com/storage/) URIs are supported. URIs must be specified in the following format: `gs://bucket-id/object-id` (other URI formats return google.rpc.Code.INVALID_ARGUMENT). For more information, see [Request URIs](https://cloud.google.com/storage/docs/request-endpoints). To identify multiple videos, a video URI may include wildcards in the `object-id`. Supported wildcards: '*' to match 0 or more characters; '?' to match 1 character. If unset, the input video should be embedded in the request as `input_content`. If set, `input_content` must be unset.",
          "type": "string"
        },
        "locationId": {
          "description": "Optional. Cloud region where annotation should take place. Supported cloud regions are: `us-east1`, `us-west1`, `europe-west1`, `asia-east1`. If no region is specified, the region will be determined based on video file location.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation",
      "description": "Annotation corresponding to one detected, tracked and recognized logo class.",
      "properties": {
        "entity": {
          "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.",
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity"
        },
        "segments": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment"
          },
          "type": "array",
          "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment."
        },
        "tracks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track"
          },
          "type": "array",
          "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames."
        }
      }
    },
    "GoogleCloudVideointelligenceV1_VideoAnnotationProgress": {
      "type": "object",
      "properties": {
        "inputUri": {
          "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).",
          "type": "string"
        },
        "exportStatus": {
          "$ref": "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus",
          "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request."
        },
        "segment": {
          "description": "Specifies which segment is being tracked if the request contains more than one segment.",
          "$ref": "GoogleCloudVideointelligenceV1_VideoSegment"
        },
        "progressPercent": {
          "type": "integer",
          "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.",
          "format": "int32"
        },
        "updateTime": {
          "format": "google-datetime",
          "type": "string",
          "description": "Time of the most recent update."
        },
        "feature": {
          "type": "string",
          "enum": [
            "FEATURE_UNSPECIFIED",
            "LABEL_DETECTION",
            "SHOT_CHANGE_DETECTION",
            "EXPLICIT_CONTENT_DETECTION",
            "FACE_DETECTION",
            "SPEECH_TRANSCRIPTION",
            "TEXT_DETECTION",
            "OBJECT_TRACKING",
            "LOGO_RECOGNITION",
            "PERSON_DETECTION"
          ],
          "enumDescriptions": [
            "Unspecified.",
            "Label detection. Detect objects, such as dog or flower.",
            "Shot change detection.",
            "Explicit content detection.",
            "Human face detection.",
            "Speech transcription.",
            "OCR text detection and tracking.",
            "Object detection and tracking.",
            "Logo detection, tracking, and recognition.",
            "Person detection."
          ],
          "description": "Specifies which feature is being tracked if the request contains more than one feature."
        },
        "startTime": {
          "type": "string",
          "format": "google-datetime",
          "description": "Time when the request was received."
        }
      },
      "description": "Annotation progress for a single video.",
      "id": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress"
    },
    "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation": {
      "id": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation",
      "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.",
      "type": "object",
      "properties": {
        "frames": {
          "description": "All video frames where explicit content was detected.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_ExplicitContentFrame"
          },
          "type": "array"
        },
        "version": {
          "description": "Feature version.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame": {
      "type": "object",
      "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.",
      "properties": {
        "normalizedBoundingBox": {
          "description": "The normalized bounding box location of this object track for the frame.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox"
        },
        "timeOffset": {
          "format": "google-duration",
          "description": "The timestamp of the frame in microseconds.",
          "type": "string"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame"
    },
    "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly",
      "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.",
      "properties": {
        "vertices": {
          "description": "Normalized vertices of the bounding polygon.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex"
          },
          "type": "array"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_LabelSegment": {
      "description": "Video segment level annotation results for label detection.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_LabelSegment",
      "properties": {
        "confidence": {
          "type": "number",
          "description": "Confidence that the label is accurate. Range: [0, 1].",
          "format": "float"
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment",
          "description": "Video segment where a label was detected."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_LabelDetectionConfig": {
      "properties": {
        "videoConfidenceThreshold": {
          "description": "The confidence threshold we perform filtering on the labels from video-level and shot-level detections. If not set, it's set to 0.3 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model.",
          "type": "number",
          "format": "float"
        },
        "stationaryCamera": {
          "type": "boolean",
          "description": "Whether the video has been shot from a stationary (i.e., non-moving) camera. When set to true, might improve detection accuracy for moving objects. Should be used with `SHOT_AND_FRAME_MODE` enabled."
        },
        "model": {
          "type": "string",
          "description": "Model to use for label detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\"."
        },
        "labelDetectionMode": {
          "enumDescriptions": [
            "Unspecified.",
            "Detect shot-level labels.",
            "Detect frame-level labels.",
            "Detect both shot-level and frame-level labels."
          ],
          "type": "string",
          "enum": [
            "LABEL_DETECTION_MODE_UNSPECIFIED",
            "SHOT_MODE",
            "FRAME_MODE",
            "SHOT_AND_FRAME_MODE"
          ],
          "description": "What labels should be detected with LABEL_DETECTION, in addition to video-level labels or segment-level labels. If unspecified, defaults to `SHOT_MODE`."
        },
        "frameConfidenceThreshold": {
          "format": "float",
          "description": "The confidence threshold we perform filtering on the labels from frame-level detection. If not set, it is set to 0.4 by default. The valid range for this threshold is [0.1, 0.9]. Any value set outside of this range will be clipped. Note: For best results, follow the default threshold. We will update the default threshold everytime when we release a new model.",
          "type": "number"
        }
      },
      "description": "Config for LABEL_DETECTION.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_LabelDetectionConfig",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame": {
      "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.",
      "properties": {
        "normalizedBoundingBox": {
          "description": "The normalized bounding box location of this object track for the frame.",
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox"
        },
        "timeOffset": {
          "description": "The timestamp of the frame in microseconds.",
          "type": "string",
          "format": "google-duration"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1_WordInfo": {
      "type": "object",
      "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`.",
      "properties": {
        "speakerTag": {
          "type": "integer",
          "format": "int32",
          "readOnly": true,
          "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled."
        },
        "confidence": {
          "type": "number",
          "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.",
          "format": "float",
          "readOnly": true
        },
        "speakerLabel": {
          "readOnly": true,
          "type": "string",
          "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word."
        },
        "word": {
          "type": "string",
          "description": "The word corresponding to this set of information."
        },
        "endTime": {
          "type": "string",
          "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.",
          "format": "google-duration"
        },
        "startTime": {
          "type": "string",
          "format": "google-duration",
          "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary."
        }
      },
      "id": "GoogleCloudVideointelligenceV1_WordInfo"
    },
    "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox": {
      "properties": {
        "left": {
          "type": "number",
          "format": "float",
          "description": "Left X coordinate."
        },
        "top": {
          "description": "Top Y coordinate.",
          "format": "float",
          "type": "number"
        },
        "right": {
          "description": "Right X coordinate.",
          "format": "float",
          "type": "number"
        },
        "bottom": {
          "type": "number",
          "format": "float",
          "description": "Bottom Y coordinate."
        }
      },
      "id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox",
      "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation": {
      "description": "Face detection annotation.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation",
      "properties": {
        "tracks": {
          "description": "The face tracks with attributes.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track"
          }
        },
        "thumbnail": {
          "type": "string",
          "description": "The thumbnail of a person's face.",
          "format": "byte"
        },
        "version": {
          "description": "Feature version.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation",
      "description": "Annotations corresponding to one tracked object.",
      "properties": {
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "entity": {
          "description": "Entity to specify the object category that this track is labeled as.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_Entity"
        },
        "frames": {
          "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame"
          }
        },
        "confidence": {
          "description": "Object category's labeling confidence of this track.",
          "format": "float",
          "type": "number"
        },
        "segment": {
          "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment"
        },
        "trackId": {
          "type": "string",
          "format": "int64",
          "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack": {
      "properties": {
        "faceTrack": {
          "description": "A track of a person's face.",
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track"
        },
        "celebrities": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity"
          },
          "description": "Top N match of the celebrities for the face in this track.",
          "type": "array"
        }
      },
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack",
      "description": "The annotation result of a celebrity face track. RecognizedCelebrity field could be empty if the face track does not have any matched celebrities."
    },
    "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation": {
      "properties": {
        "segments": {
          "description": "All video segments where a label was detected.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment"
          }
        },
        "categoryEntities": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity"
          },
          "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.",
          "type": "array"
        },
        "entity": {
          "description": "Detected entity.",
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity"
        },
        "frames": {
          "description": "All video frames where a label was detected.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame"
          }
        },
        "version": {
          "type": "string",
          "description": "Feature version."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation",
      "type": "object",
      "description": "Label annotation."
    },
    "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionConfig": {
      "type": "object",
      "properties": {
        "includeBoundingBoxes": {
          "type": "boolean",
          "description": "Whether bounding boxes are included in the person detection annotation output."
        },
        "includePoseLandmarks": {
          "description": "Whether to enable pose landmarks detection. Ignored if 'include_bounding_boxes' is set to false.",
          "type": "boolean"
        },
        "includeAttributes": {
          "description": "Whether to enable person attributes detection, such as cloth color (black, blue, etc), type (coat, dress, etc), pattern (plain, floral, etc), hair, etc. Ignored if 'include_bounding_boxes' is set to false.",
          "type": "boolean"
        }
      },
      "description": "Config for PERSON_DETECTION.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionConfig"
    },
    "GoogleCloudVideointelligenceV1_AnnotateVideoProgress": {
      "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
      "id": "GoogleCloudVideointelligenceV1_AnnotateVideoProgress",
      "type": "object",
      "properties": {
        "annotationProgress": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationProgress"
          },
          "type": "array",
          "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly": {
      "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingPoly",
      "type": "object",
      "properties": {
        "vertices": {
          "description": "Normalized vertices of the bounding polygon.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex"
          }
        }
      }
    },
    "GoogleCloudVideointelligenceV1beta2_WordInfo": {
      "id": "GoogleCloudVideointelligenceV1beta2_WordInfo",
      "properties": {
        "startTime": {
          "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.",
          "format": "google-duration",
          "type": "string"
        },
        "confidence": {
          "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.",
          "type": "number",
          "readOnly": true,
          "format": "float"
        },
        "word": {
          "type": "string",
          "description": "The word corresponding to this set of information."
        },
        "endTime": {
          "type": "string",
          "format": "google-duration",
          "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary."
        },
        "speakerTag": {
          "type": "integer",
          "readOnly": true,
          "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.",
          "format": "int32"
        },
        "speakerLabel": {
          "readOnly": true,
          "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.",
          "type": "string"
        }
      },
      "type": "object",
      "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`."
    },
    "GoogleLongrunning_Operation": {
      "type": "object",
      "properties": {
        "done": {
          "type": "boolean",
          "description": "If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available."
        },
        "error": {
          "description": "The error result of the operation in case of failure or cancellation.",
          "$ref": "GoogleRpc_Status"
        },
        "metadata": {
          "additionalProperties": {
            "type": "any",
            "description": "Properties of the object. Contains field @type with type URL."
          },
          "description": "Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.",
          "type": "object"
        },
        "response": {
          "additionalProperties": {
            "type": "any",
            "description": "Properties of the object. Contains field @type with type URL."
          },
          "description": "The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.",
          "type": "object"
        },
        "name": {
          "description": "The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.",
          "type": "string"
        }
      },
      "id": "GoogleLongrunning_Operation",
      "description": "This resource represents a long-running operation that is the result of a network API call."
    },
    "GoogleCloudVideointelligenceV1beta2_TextSegment": {
      "type": "object",
      "description": "Video segment level annotation results for text detection.",
      "id": "GoogleCloudVideointelligenceV1beta2_TextSegment",
      "properties": {
        "confidence": {
          "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears.",
          "format": "float",
          "type": "number"
        },
        "frames": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_TextFrame"
          },
          "type": "array",
          "description": "Information related to the frames where OCR detected text appears."
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment",
          "description": "Video segment where a text snippet was detected."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingConfig": {
      "type": "object",
      "description": "Config for OBJECT_TRACKING.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingConfig",
      "properties": {
        "model": {
          "description": "Model to use for object tracking. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject": {
      "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.",
      "id": "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject",
      "type": "object",
      "properties": {
        "landmarks": {
          "description": "Optional. The detected landmarks.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark"
          }
        },
        "timeOffset": {
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.",
          "type": "string"
        },
        "attributes": {
          "description": "Optional. The attributes of the object in the bounding box.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute"
          },
          "type": "array"
        },
        "normalizedBoundingBox": {
          "description": "Normalized Bounding box in a frame, where the object is located.",
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox"
        }
      }
    },
    "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation": {
      "description": "Face detection annotation.",
      "id": "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation",
      "type": "object",
      "properties": {
        "thumbnail": {
          "type": "string",
          "format": "byte",
          "description": "The thumbnail of a person's face."
        },
        "tracks": {
          "description": "The face tracks with attributes.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_Track"
          }
        },
        "version": {
          "description": "Feature version.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_FaceSegment": {
      "id": "GoogleCloudVideointelligenceV1p3beta1_FaceSegment",
      "type": "object",
      "description": "Video segment level annotation results for face detection.",
      "properties": {
        "segment": {
          "description": "Video segment where a face was detected.",
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_Entity": {
      "id": "GoogleCloudVideointelligenceV1p3beta1_Entity",
      "description": "Detected entity from video analysis.",
      "properties": {
        "entityId": {
          "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).",
          "type": "string"
        },
        "languageCode": {
          "type": "string",
          "description": "Language code for `description` in BCP-47 format."
        },
        "description": {
          "description": "Textual description, e.g., `Fixed-gear bicycle`.",
          "type": "string"
        }
      },
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation": {
      "type": "object",
      "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.",
      "properties": {
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "frames": {
          "type": "array",
          "description": "All video frames where explicit content was detected.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame"
          }
        }
      },
      "id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation"
    },
    "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame",
      "type": "object",
      "description": "Video frame level annotation results for explicit content.",
      "properties": {
        "timeOffset": {
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.",
          "type": "string"
        },
        "pornographyLikelihood": {
          "description": "Likelihood of the pornography content..",
          "type": "string",
          "enum": [
            "LIKELIHOOD_UNSPECIFIED",
            "VERY_UNLIKELY",
            "UNLIKELY",
            "POSSIBLE",
            "LIKELY",
            "VERY_LIKELY"
          ],
          "enumDescriptions": [
            "Unspecified likelihood.",
            "Very unlikely.",
            "Unlikely.",
            "Possible.",
            "Likely.",
            "Very likely."
          ]
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_FaceSegment": {
      "properties": {
        "segment": {
          "description": "Video segment where a face was detected.",
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p1beta1_FaceSegment",
      "description": "Video segment level annotation results for face detection.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p2beta1_FaceFrame": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_FaceFrame",
      "deprecated": true,
      "type": "object",
      "description": "Deprecated. No effect.",
      "properties": {
        "normalizedBoundingBoxes": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox"
          },
          "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.",
          "type": "array"
        },
        "timeOffset": {
          "format": "google-duration",
          "type": "string",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex": {
      "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex",
      "properties": {
        "y": {
          "type": "number",
          "format": "float",
          "description": "Y coordinate."
        },
        "x": {
          "type": "number",
          "format": "float",
          "description": "X coordinate."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation": {
      "type": "object",
      "properties": {
        "tracks": {
          "description": "The face tracks with attributes.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track"
          }
        },
        "thumbnail": {
          "description": "The thumbnail of a person's face.",
          "type": "string",
          "format": "byte"
        },
        "version": {
          "description": "Feature version.",
          "type": "string"
        }
      },
      "description": "Face detection annotation.",
      "id": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation"
    },
    "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults": {
      "properties": {
        "textAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation"
          },
          "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.",
          "type": "array"
        },
        "segmentLabelAnnotations": {
          "type": "array",
          "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation"
          }
        },
        "inputUri": {
          "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).",
          "type": "string"
        },
        "shotLabelAnnotations": {
          "description": "Topical label annotations on shot level. There is exactly one element for each unique label.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation"
          },
          "type": "array"
        },
        "error": {
          "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.",
          "$ref": "GoogleRpc_Status"
        },
        "speechTranscriptions": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription"
          },
          "description": "Speech transcription.",
          "type": "array"
        },
        "frameLabelAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation"
          },
          "description": "Label annotations on frame level. There is exactly one element for each unique label."
        },
        "segmentPresenceLabelAnnotations": {
          "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation"
          }
        },
        "shotAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment"
          },
          "description": "Shot annotations. Each shot is represented as a video segment.",
          "type": "array"
        },
        "objectAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation"
          },
          "description": "Annotations for list of objects detected and tracked in video.",
          "type": "array"
        },
        "logoRecognitionAnnotations": {
          "description": "Annotations for list of logos detected, tracked and recognized in video.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_LogoRecognitionAnnotation"
          },
          "type": "array"
        },
        "personDetectionAnnotations": {
          "description": "Person detection annotations.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation"
          },
          "type": "array"
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment",
          "description": "Video segment on which the annotation is run."
        },
        "explicitAnnotation": {
          "description": "Explicit content annotation.",
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation"
        },
        "faceAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation"
          },
          "deprecated": true,
          "description": "Deprecated. Please use `face_detection_annotations` instead."
        },
        "faceDetectionAnnotations": {
          "description": "Face detection annotations.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceDetectionAnnotation"
          },
          "type": "array"
        },
        "celebrityRecognitionAnnotations": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation",
          "description": "Celebrity recognition annotations."
        },
        "shotPresenceLabelAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation"
          },
          "type": "array",
          "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request."
        }
      },
      "description": "Annotation results for a single video.",
      "id": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus": {
      "properties": {
        "status": {
          "readOnly": true,
          "description": "Output only. Only set if state is FAILED.",
          "$ref": "GoogleRpc_Status"
        },
        "state": {
          "description": "Output only. State of the `output_uri` export.",
          "enumDescriptions": [
            "Default value.",
            "Export succeeded.",
            "Export failed."
          ],
          "type": "string",
          "enum": [
            "STATE_UNSPECIFIED",
            "SUCCEEDED",
            "FAILED"
          ],
          "readOnly": true
        }
      },
      "id": "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus",
      "type": "object",
      "description": "Status of exporting annotation response to user specified `output_uri`."
    },
    "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative",
      "description": "Alternative hypotheses (a.k.a. n-best list).",
      "properties": {
        "words": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_WordInfo"
          },
          "readOnly": true,
          "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.",
          "type": "array"
        },
        "transcript": {
          "type": "string",
          "description": "Transcript text representing the words that the user spoke."
        },
        "confidence": {
          "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.",
          "type": "number",
          "readOnly": true,
          "format": "float"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_FaceFrame": {
      "id": "GoogleCloudVideointelligenceV1p3beta1_FaceFrame",
      "description": "Deprecated. No effect.",
      "properties": {
        "timeOffset": {
          "format": "google-duration",
          "type": "string",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location."
        },
        "normalizedBoundingBoxes": {
          "type": "array",
          "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox"
          }
        }
      },
      "deprecated": true,
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1_Track": {
      "id": "GoogleCloudVideointelligenceV1_Track",
      "description": "A track of an object instance.",
      "type": "object",
      "properties": {
        "confidence": {
          "type": "number",
          "description": "Optional. The confidence score of the tracked object.",
          "format": "float"
        },
        "segment": {
          "description": "Video segment of a track.",
          "$ref": "GoogleCloudVideointelligenceV1_VideoSegment"
        },
        "timestampedObjects": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_TimestampedObject"
          },
          "description": "The object with timestamp and attributes per frame in the track.",
          "type": "array"
        },
        "attributes": {
          "description": "Optional. Attributes in the track level.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_DetectedAttribute"
          }
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_Track": {
      "properties": {
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment",
          "description": "Video segment of a track."
        },
        "attributes": {
          "description": "Optional. Attributes in the track level.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute"
          },
          "type": "array"
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Optional. The confidence score of the tracked object."
        },
        "timestampedObjects": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_TimestampedObject"
          },
          "description": "The object with timestamp and attributes per frame in the track.",
          "type": "array"
        }
      },
      "type": "object",
      "description": "A track of an object instance.",
      "id": "GoogleCloudVideointelligenceV1p3beta1_Track"
    },
    "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation": {
      "id": "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation",
      "description": "Annotation corresponding to one detected, tracked and recognized logo class.",
      "type": "object",
      "properties": {
        "tracks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_Track"
          },
          "type": "array",
          "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames."
        },
        "entity": {
          "$ref": "GoogleCloudVideointelligenceV1_Entity",
          "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as."
        },
        "segments": {
          "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_VideoSegment"
          },
          "type": "array"
        }
      }
    },
    "GoogleCloudVideointelligenceV1_FaceSegment": {
      "description": "Video segment level annotation results for face detection.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1_FaceSegment",
      "properties": {
        "segment": {
          "description": "Video segment where a face was detected.",
          "$ref": "GoogleCloudVideointelligenceV1_VideoSegment"
        }
      }
    },
    "GoogleCloudVideointelligenceV1beta2_Track": {
      "properties": {
        "segment": {
          "description": "Video segment of a track.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment"
        },
        "attributes": {
          "description": "Optional. Attributes in the track level.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute"
          },
          "type": "array"
        },
        "timestampedObjects": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_TimestampedObject"
          },
          "description": "The object with timestamp and attributes per frame in the track."
        },
        "confidence": {
          "description": "Optional. The confidence score of the tracked object.",
          "type": "number",
          "format": "float"
        }
      },
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_Track",
      "description": "A track of an object instance."
    },
    "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation": {
      "description": "Face detection annotation.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation",
      "type": "object",
      "properties": {
        "thumbnail": {
          "type": "string",
          "description": "The thumbnail of a person's face.",
          "format": "byte"
        },
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "tracks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track"
          },
          "description": "The face tracks with attributes.",
          "type": "array"
        }
      }
    },
    "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse": {
      "properties": {
        "annotationResults": {
          "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults"
          },
          "type": "array"
        }
      },
      "type": "object",
      "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
      "id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoResponse"
    },
    "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription": {
      "id": "GoogleCloudVideointelligenceV1p3beta1_SpeechTranscription",
      "properties": {
        "alternatives": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_SpeechRecognitionAlternative"
          },
          "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer."
        },
        "languageCode": {
          "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.",
          "readOnly": true,
          "type": "string"
        }
      },
      "type": "object",
      "description": "A speech recognition result corresponding to a portion of the audio."
    },
    "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation": {
      "id": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation",
      "properties": {
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "tracks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track"
          },
          "type": "array",
          "description": "The detected tracks of a person."
        }
      },
      "description": "Person detection annotation per video.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1_SpeechTranscription": {
      "description": "A speech recognition result corresponding to a portion of the audio.",
      "type": "object",
      "properties": {
        "alternatives": {
          "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative"
          },
          "type": "array"
        },
        "languageCode": {
          "type": "string",
          "readOnly": true,
          "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio."
        }
      },
      "id": "GoogleCloudVideointelligenceV1_SpeechTranscription"
    },
    "GoogleCloudVideointelligenceV1_FaceFrame": {
      "properties": {
        "normalizedBoundingBoxes": {
          "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox"
          }
        },
        "timeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location."
        }
      },
      "id": "GoogleCloudVideointelligenceV1_FaceFrame",
      "description": "Deprecated. No effect.",
      "deprecated": true,
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute": {
      "type": "object",
      "description": "A generic detected attribute represented by name in string format.",
      "properties": {
        "confidence": {
          "description": "Detected attribute confidence. Range [0, 1].",
          "format": "float",
          "type": "number"
        },
        "value": {
          "type": "string",
          "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc."
        },
        "name": {
          "type": "string",
          "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute"
    },
    "GoogleCloudVideointelligenceV1_TimestampedObject": {
      "id": "GoogleCloudVideointelligenceV1_TimestampedObject",
      "properties": {
        "normalizedBoundingBox": {
          "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox",
          "description": "Normalized Bounding box in a frame, where the object is located."
        },
        "landmarks": {
          "description": "Optional. The detected landmarks.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_DetectedLandmark"
          }
        },
        "attributes": {
          "description": "Optional. The attributes of the object in the bounding box.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_DetectedAttribute"
          },
          "type": "array"
        },
        "timeOffset": {
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.",
          "type": "string",
          "format": "google-duration"
        }
      },
      "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1_ExplicitContentFrame": {
      "type": "object",
      "properties": {
        "timeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location."
        },
        "pornographyLikelihood": {
          "enumDescriptions": [
            "Unspecified likelihood.",
            "Very unlikely.",
            "Unlikely.",
            "Possible.",
            "Likely.",
            "Very likely."
          ],
          "type": "string",
          "enum": [
            "LIKELIHOOD_UNSPECIFIED",
            "VERY_UNLIKELY",
            "UNLIKELY",
            "POSSIBLE",
            "LIKELY",
            "VERY_LIKELY"
          ],
          "description": "Likelihood of the pornography content.."
        }
      },
      "description": "Video frame level annotation results for explicit content.",
      "id": "GoogleCloudVideointelligenceV1_ExplicitContentFrame"
    },
    "GoogleCloudVideointelligenceV1beta2_VideoSegment": {
      "properties": {
        "endTimeOffset": {
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).",
          "type": "string"
        },
        "startTimeOffset": {
          "type": "string",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive).",
          "format": "google-duration"
        }
      },
      "description": "Video segment.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_VideoSegment"
    },
    "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoProgress": {
      "properties": {
        "annotationProgress": {
          "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress"
          }
        }
      },
      "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
      "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoProgress",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation": {
      "properties": {
        "version": {
          "type": "string",
          "description": "Feature version."
        },
        "frames": {
          "type": "array",
          "description": "All video frames where explicit content was detected.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame"
          }
        }
      },
      "type": "object",
      "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.",
      "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation"
    },
    "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation": {
      "type": "object",
      "properties": {
        "tracks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_Track"
          },
          "description": "The detected tracks of a person.",
          "type": "array"
        },
        "version": {
          "description": "Feature version.",
          "type": "string"
        }
      },
      "id": "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation",
      "description": "Person detection annotation per video."
    },
    "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation": {
      "description": "Annotation corresponding to one detected, tracked and recognized logo class.",
      "properties": {
        "tracks": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_Track"
          },
          "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames."
        },
        "segments": {
          "type": "array",
          "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment"
          }
        },
        "entity": {
          "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.",
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity"
        }
      },
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation"
    },
    "GoogleCloudVideointelligenceV1p2beta1_WordInfo": {
      "properties": {
        "speakerLabel": {
          "type": "string",
          "description": "Output only. A distinct string value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word.",
          "readOnly": true
        },
        "startTime": {
          "format": "google-duration",
          "description": "Time offset relative to the beginning of the audio, and corresponding to the start of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.",
          "type": "string"
        },
        "word": {
          "type": "string",
          "description": "The word corresponding to this set of information."
        },
        "confidence": {
          "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.",
          "readOnly": true,
          "format": "float",
          "type": "number"
        },
        "speakerTag": {
          "type": "integer",
          "format": "int32",
          "description": "Output only. A distinct integer value is assigned for every speaker within the audio. This field specifies which one of those speakers was detected to have spoken this word. Value ranges from 1 up to diarization_speaker_count, and is only set if speaker diarization is enabled.",
          "readOnly": true
        },
        "endTime": {
          "type": "string",
          "description": "Time offset relative to the beginning of the audio, and corresponding to the end of the spoken word. This field is only set if `enable_word_time_offsets=true` and only in the top hypothesis. This is an experimental feature and the accuracy of the time offset can vary.",
          "format": "google-duration"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_WordInfo",
      "type": "object",
      "description": "Word-specific information for recognized words. Word information is only included in the response when certain request parameters are set, such as `enable_word_time_offsets`."
    },
    "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress": {
      "description": "Annotation progress for a single video.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress",
      "properties": {
        "updateTime": {
          "description": "Time of the most recent update.",
          "format": "google-datetime",
          "type": "string"
        },
        "exportStatus": {
          "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.",
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExportToOutputUriStatus"
        },
        "startTime": {
          "description": "Time when the request was received.",
          "format": "google-datetime",
          "type": "string"
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment",
          "description": "Specifies which segment is being tracked if the request contains more than one segment."
        },
        "feature": {
          "description": "Specifies which feature is being tracked if the request contains more than one feature.",
          "enumDescriptions": [
            "Unspecified.",
            "Label detection. Detect objects, such as dog or flower.",
            "Shot change detection.",
            "Explicit content detection.",
            "Human face detection.",
            "Speech transcription.",
            "OCR text detection and tracking.",
            "Object detection and tracking.",
            "Logo detection, tracking, and recognition.",
            "Person detection."
          ],
          "type": "string",
          "enum": [
            "FEATURE_UNSPECIFIED",
            "LABEL_DETECTION",
            "SHOT_CHANGE_DETECTION",
            "EXPLICIT_CONTENT_DETECTION",
            "FACE_DETECTION",
            "SPEECH_TRANSCRIPTION",
            "TEXT_DETECTION",
            "OBJECT_TRACKING",
            "LOGO_RECOGNITION",
            "PERSON_DETECTION"
          ]
        },
        "progressPercent": {
          "format": "int32",
          "type": "integer",
          "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed."
        },
        "inputUri": {
          "type": "string",
          "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)."
        }
      }
    },
    "GoogleCloudVideointelligenceV1_AnnotateVideoResponse": {
      "properties": {
        "annotationResults": {
          "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_VideoAnnotationResults"
          }
        }
      },
      "id": "GoogleCloudVideointelligenceV1_AnnotateVideoResponse",
      "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative",
      "description": "Alternative hypotheses (a.k.a. n-best list).",
      "properties": {
        "confidence": {
          "format": "float",
          "type": "number",
          "readOnly": true,
          "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set."
        },
        "words": {
          "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.",
          "readOnly": true,
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_WordInfo"
          },
          "type": "array"
        },
        "transcript": {
          "description": "Transcript text representing the words that the user spoke.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly": {
      "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly",
      "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.",
      "properties": {
        "vertices": {
          "type": "array",
          "description": "Normalized vertices of the bounding polygon.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex"
          }
        }
      },
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p2beta1_SpeechContext": {
      "properties": {
        "phrases": {
          "description": "Optional. A list of strings containing words and phrases \"hints\" so that the speech recognition is more likely to recognize them. This can be used to improve the accuracy for specific words and phrases, for example, if specific commands are typically spoken by the user. This can also be used to add additional words to the vocabulary of the recognizer. See [usage limits](https://cloud.google.com/speech/limits#content).",
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "type": "object",
      "description": "Provides \"hints\" to the speech recognizer to favor specific words and phrases in the results.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechContext"
    },
    "GoogleCloudVideointelligenceV1_NormalizedVertex": {
      "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.",
      "id": "GoogleCloudVideointelligenceV1_NormalizedVertex",
      "type": "object",
      "properties": {
        "x": {
          "description": "X coordinate.",
          "type": "number",
          "format": "float"
        },
        "y": {
          "format": "float",
          "description": "Y coordinate.",
          "type": "number"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentDetectionConfig": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentDetectionConfig",
      "type": "object",
      "properties": {
        "model": {
          "description": "Model to use for explicit content detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\".",
          "type": "string"
        }
      },
      "description": "Config for EXPLICIT_CONTENT_DETECTION."
    },
    "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute": {
      "description": "A generic detected attribute represented by name in string format.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute",
      "type": "object",
      "properties": {
        "name": {
          "type": "string",
          "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document."
        },
        "value": {
          "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.",
          "type": "string"
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Detected attribute confidence. Range [0, 1]."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscriptionConfig": {
      "description": "Config for SPEECH_TRANSCRIPTION.",
      "properties": {
        "enableAutomaticPunctuation": {
          "type": "boolean",
          "description": "Optional. If 'true', adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default 'false' value does not add punctuation to result hypotheses. NOTE: \"This is currently offered as an experimental service, complimentary to all users. In the future this may be exclusively available as a premium feature.\""
        },
        "diarizationSpeakerCount": {
          "type": "integer",
          "format": "int32",
          "description": "Optional. If set, specifies the estimated number of speakers in the conversation. If not set, defaults to '2'. Ignored unless enable_speaker_diarization is set to true."
        },
        "speechContexts": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechContext"
          },
          "type": "array",
          "description": "Optional. A means to provide context to assist the speech recognition."
        },
        "audioOutputUriPrefix": {
          "description": "Optional. Legacy field. This field must be a Cloud Storage URI prefix. (e.g., `gs://bucket/path/`).",
          "type": "string"
        },
        "enableWordConfidence": {
          "description": "Optional. If `true`, the top result includes a list of words and the confidence for those words. If `false`, no word-level confidence information is returned. The default is `false`.",
          "type": "boolean"
        },
        "maxAlternatives": {
          "format": "int32",
          "type": "integer",
          "description": "Optional. Maximum number of recognition hypotheses to be returned. Specifically, the maximum number of `SpeechRecognitionAlternative` messages within each `SpeechTranscription`. The server may return fewer than `max_alternatives`. Valid values are `0`-`30`. A value of `0` or `1` will return a maximum of one. If omitted, will return a maximum of one."
        },
        "filterProfanity": {
          "description": "Optional. If set to `true`, the server will attempt to filter out profanities, replacing all but the initial character in each filtered word with asterisks, e.g. \"f***\". If set to `false` or omitted, profanities won't be filtered out.",
          "type": "boolean"
        },
        "languageCode": {
          "description": "Required. *Required* The language of the supplied audio as a [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag. Example: \"en-US\". See [Language Support](https://cloud.google.com/speech/docs/languages) for a list of the currently supported language codes.",
          "type": "string"
        },
        "audioTracks": {
          "type": "array",
          "description": "Optional. For file formats, such as MXF or MKV, supporting multiple audio tracks, specify up to two tracks. Default: track 0.",
          "items": {
            "format": "int32",
            "type": "integer"
          }
        },
        "enableSpeakerDiarization": {
          "type": "boolean",
          "description": "Optional. If 'true', enables speaker detection for each recognized word in the top alternative of the recognition result using a speaker_tag provided in the WordInfo. Note: When this is true, we send all the words from the beginning of the audio for the top alternative in every consecutive response. This is done in order to improve our speaker tags as our models learn to identify the speakers in the conversation over time."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscriptionConfig",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p3beta1_TextFrame": {
      "properties": {
        "timeOffset": {
          "format": "google-duration",
          "description": "Timestamp of this frame.",
          "type": "string"
        },
        "rotatedBoundingBox": {
          "description": "Bounding polygon of the detected text for this frame.",
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingPoly"
        }
      },
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_TextFrame",
      "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets."
    },
    "GoogleCloudVideointelligenceV1beta2_LabelAnnotation": {
      "description": "Label annotation.",
      "id": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation",
      "properties": {
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "segments": {
          "description": "All video segments where a label was detected.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_LabelSegment"
          }
        },
        "entity": {
          "description": "Detected entity.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_Entity"
        },
        "frames": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_LabelFrame"
          },
          "type": "array",
          "description": "All video frames where a label was detected."
        },
        "categoryEntities": {
          "type": "array",
          "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_Entity"
          }
        }
      },
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation": {
      "properties": {
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1_VideoSegment",
          "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears."
        },
        "trackId": {
          "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.",
          "type": "string",
          "format": "int64"
        },
        "entity": {
          "description": "Entity to specify the object category that this track is labeled as.",
          "$ref": "GoogleCloudVideointelligenceV1_Entity"
        },
        "frames": {
          "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingFrame"
          }
        },
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "confidence": {
          "type": "number",
          "description": "Object category's labeling confidence of this track.",
          "format": "float"
        }
      },
      "id": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation",
      "type": "object",
      "description": "Annotations corresponding to one tracked object."
    },
    "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation": {
      "type": "object",
      "properties": {
        "version": {
          "type": "string",
          "description": "Feature version."
        },
        "celebrityTracks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_CelebrityTrack"
          },
          "type": "array",
          "description": "The tracks detected from the input video, including recognized celebrities and other detected faces in the video."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p3beta1_CelebrityRecognitionAnnotation",
      "description": "Celebrity recognition annotation per video."
    },
    "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark": {
      "properties": {
        "point": {
          "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.",
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedVertex"
        },
        "confidence": {
          "description": "The confidence score of the detected landmark. Range [0, 1].",
          "type": "number",
          "format": "float"
        },
        "name": {
          "description": "The name of this landmark, for example, left_hand, right_shoulder.",
          "type": "string"
        }
      },
      "type": "object",
      "description": "A generic detected landmark represented by name in string format and a 2D location.",
      "id": "GoogleCloudVideointelligenceV1p3beta1_DetectedLandmark"
    },
    "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus": {
      "properties": {
        "status": {
          "readOnly": true,
          "description": "Output only. Only set if state is FAILED.",
          "$ref": "GoogleRpc_Status"
        },
        "state": {
          "description": "Output only. State of the `output_uri` export.",
          "type": "string",
          "enum": [
            "STATE_UNSPECIFIED",
            "SUCCEEDED",
            "FAILED"
          ],
          "readOnly": true,
          "enumDescriptions": [
            "Default value.",
            "Export succeeded.",
            "Export failed."
          ]
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus",
      "type": "object",
      "description": "Status of exporting annotation response to user specified `output_uri`."
    },
    "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation": {
      "description": "Face detection annotation.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation",
      "properties": {
        "tracks": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_Track"
          },
          "description": "The face tracks with attributes."
        },
        "version": {
          "type": "string",
          "description": "Feature version."
        },
        "thumbnail": {
          "format": "byte",
          "type": "string",
          "description": "The thumbnail of a person's face."
        }
      }
    },
    "GoogleCloudVideointelligenceV1beta2_DetectedAttribute": {
      "description": "A generic detected attribute represented by name in string format.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute",
      "properties": {
        "value": {
          "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.",
          "type": "string"
        },
        "confidence": {
          "description": "Detected attribute confidence. Range [0, 1].",
          "format": "float",
          "type": "number"
        },
        "name": {
          "type": "string",
          "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document."
        }
      }
    },
    "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationResults",
      "properties": {
        "segmentLabelAnnotations": {
          "type": "array",
          "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation"
          }
        },
        "logoRecognitionAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation"
          },
          "type": "array",
          "description": "Annotations for list of logos detected, tracked and recognized in video."
        },
        "segmentPresenceLabelAnnotations": {
          "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation"
          }
        },
        "objectAnnotations": {
          "description": "Annotations for list of objects detected and tracked in video.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingAnnotation"
          },
          "type": "array"
        },
        "personDetectionAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_PersonDetectionAnnotation"
          },
          "type": "array",
          "description": "Person detection annotations."
        },
        "speechTranscriptions": {
          "description": "Speech transcription.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_SpeechTranscription"
          }
        },
        "textAnnotations": {
          "type": "array",
          "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_TextAnnotation"
          }
        },
        "shotPresenceLabelAnnotations": {
          "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation"
          },
          "type": "array"
        },
        "shotLabelAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation"
          },
          "description": "Topical label annotations on shot level. There is exactly one element for each unique label.",
          "type": "array"
        },
        "faceDetectionAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_FaceDetectionAnnotation"
          },
          "description": "Face detection annotations.",
          "type": "array"
        },
        "shotAnnotations": {
          "type": "array",
          "description": "Shot annotations. Each shot is represented as a video segment.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment"
          }
        },
        "error": {
          "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.",
          "$ref": "GoogleRpc_Status"
        },
        "frameLabelAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_LabelAnnotation"
          },
          "description": "Label annotations on frame level. There is exactly one element for each unique label.",
          "type": "array"
        },
        "inputUri": {
          "type": "string",
          "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)."
        },
        "explicitAnnotation": {
          "description": "Explicit content annotation.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_ExplicitContentAnnotation"
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment",
          "description": "Video segment on which the annotation is run."
        },
        "faceAnnotations": {
          "deprecated": true,
          "description": "Deprecated. Please use `face_detection_annotations` instead.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_FaceAnnotation"
          },
          "type": "array"
        }
      },
      "description": "Annotation results for a single video."
    },
    "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame": {
      "type": "object",
      "description": "Video frame level annotation results for explicit content.",
      "properties": {
        "pornographyLikelihood": {
          "type": "string",
          "enum": [
            "LIKELIHOOD_UNSPECIFIED",
            "VERY_UNLIKELY",
            "UNLIKELY",
            "POSSIBLE",
            "LIKELY",
            "VERY_LIKELY"
          ],
          "description": "Likelihood of the pornography content..",
          "enumDescriptions": [
            "Unspecified likelihood.",
            "Very unlikely.",
            "Unlikely.",
            "Possible.",
            "Likely.",
            "Very likely."
          ]
        },
        "timeOffset": {
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.",
          "format": "google-duration",
          "type": "string"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentFrame"
    },
    "GoogleCloudVideointelligenceV1_LabelFrame": {
      "type": "object",
      "description": "Video frame level annotation results for label detection.",
      "properties": {
        "timeOffset": {
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.",
          "type": "string",
          "format": "google-duration"
        },
        "confidence": {
          "description": "Confidence that the label is accurate. Range: [0, 1].",
          "format": "float",
          "type": "number"
        }
      },
      "id": "GoogleCloudVideointelligenceV1_LabelFrame"
    },
    "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_DetectedLandmark",
      "properties": {
        "name": {
          "type": "string",
          "description": "The name of this landmark, for example, left_hand, right_shoulder."
        },
        "point": {
          "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex"
        },
        "confidence": {
          "type": "number",
          "description": "The confidence score of the detected landmark. Range [0, 1].",
          "format": "float"
        }
      },
      "description": "A generic detected landmark represented by name in string format and a 2D location.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1_VideoAnnotationResults": {
      "properties": {
        "faceAnnotations": {
          "description": "Deprecated. Please use `face_detection_annotations` instead.",
          "deprecated": true,
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_FaceAnnotation"
          }
        },
        "personDetectionAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation"
          },
          "description": "Person detection annotations."
        },
        "shotLabelAnnotations": {
          "type": "array",
          "description": "Topical label annotations on shot level. There is exactly one element for each unique label.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation"
          }
        },
        "logoRecognitionAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_LogoRecognitionAnnotation"
          },
          "description": "Annotations for list of logos detected, tracked and recognized in video."
        },
        "speechTranscriptions": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_SpeechTranscription"
          },
          "description": "Speech transcription."
        },
        "frameLabelAnnotations": {
          "description": "Label annotations on frame level. There is exactly one element for each unique label.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation"
          },
          "type": "array"
        },
        "error": {
          "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail.",
          "$ref": "GoogleRpc_Status"
        },
        "objectAnnotations": {
          "description": "Annotations for list of objects detected and tracked in video.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_ObjectTrackingAnnotation"
          }
        },
        "shotAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_VideoSegment"
          },
          "description": "Shot annotations. Each shot is represented as a video segment."
        },
        "faceDetectionAnnotations": {
          "description": "Face detection annotations.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_FaceDetectionAnnotation"
          }
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1_VideoSegment",
          "description": "Video segment on which the annotation is run."
        },
        "shotPresenceLabelAnnotations": {
          "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation"
          }
        },
        "segmentLabelAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation"
          },
          "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label."
        },
        "explicitAnnotation": {
          "description": "Explicit content annotation.",
          "$ref": "GoogleCloudVideointelligenceV1_ExplicitContentAnnotation"
        },
        "segmentPresenceLabelAnnotations": {
          "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_LabelAnnotation"
          }
        },
        "textAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_TextAnnotation"
          },
          "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.",
          "type": "array"
        },
        "inputUri": {
          "type": "string",
          "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)."
        }
      },
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1_VideoAnnotationResults",
      "description": "Annotation results for a single video."
    },
    "GoogleCloudVideointelligenceV1p3beta1_TextSegment": {
      "description": "Video segment level annotation results for text detection.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_TextSegment",
      "properties": {
        "segment": {
          "description": "Video segment where a text snippet was detected.",
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment"
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears."
        },
        "frames": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextFrame"
          },
          "description": "Information related to the frames where OCR detected text appears.",
          "type": "array"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_LabelFrame": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p1beta1_LabelFrame",
      "description": "Video frame level annotation results for label detection.",
      "properties": {
        "timeOffset": {
          "type": "string",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.",
          "format": "google-duration"
        },
        "confidence": {
          "type": "number",
          "description": "Confidence that the label is accurate. Range: [0, 1].",
          "format": "float"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress": {
      "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoProgress",
      "properties": {
        "annotationProgress": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress"
          },
          "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.",
          "type": "array"
        }
      },
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p1beta1_Track": {
      "type": "object",
      "properties": {
        "confidence": {
          "format": "float",
          "description": "Optional. The confidence score of the tracked object.",
          "type": "number"
        },
        "attributes": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute"
          },
          "description": "Optional. Attributes in the track level."
        },
        "timestampedObjects": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject"
          },
          "description": "The object with timestamp and attributes per frame in the track.",
          "type": "array"
        },
        "segment": {
          "description": "Video segment of a track.",
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p1beta1_Track",
      "description": "A track of an object instance."
    },
    "GoogleCloudVideointelligenceV1beta2_FaceFrame": {
      "deprecated": true,
      "properties": {
        "normalizedBoundingBoxes": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox"
          },
          "type": "array",
          "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame."
        },
        "timeOffset": {
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.",
          "type": "string"
        }
      },
      "type": "object",
      "description": "Deprecated. No effect.",
      "id": "GoogleCloudVideointelligenceV1beta2_FaceFrame"
    },
    "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative": {
      "type": "object",
      "description": "Alternative hypotheses (a.k.a. n-best list).",
      "id": "GoogleCloudVideointelligenceV1beta2_SpeechRecognitionAlternative",
      "properties": {
        "confidence": {
          "type": "number",
          "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.",
          "readOnly": true,
          "format": "float"
        },
        "transcript": {
          "description": "Transcript text representing the words that the user spoke.",
          "type": "string"
        },
        "words": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_WordInfo"
          },
          "type": "array",
          "readOnly": true,
          "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio."
        }
      }
    },
    "GoogleCloudVideointelligenceV1beta2_LabelSegment": {
      "id": "GoogleCloudVideointelligenceV1beta2_LabelSegment",
      "properties": {
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment",
          "description": "Video segment where a label was detected."
        },
        "confidence": {
          "type": "number",
          "description": "Confidence that the label is accurate. Range: [0, 1].",
          "format": "float"
        }
      },
      "type": "object",
      "description": "Video segment level annotation results for label detection."
    },
    "GoogleCloudVideointelligenceV1_VideoSegment": {
      "type": "object",
      "description": "Video segment.",
      "id": "GoogleCloudVideointelligenceV1_VideoSegment",
      "properties": {
        "startTimeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive)."
        },
        "endTimeOffset": {
          "format": "google-duration",
          "type": "string",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive)."
        }
      }
    },
    "GoogleCloudVideointelligenceV1_LabelSegment": {
      "id": "GoogleCloudVideointelligenceV1_LabelSegment",
      "properties": {
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Confidence that the label is accurate. Range: [0, 1]."
        },
        "segment": {
          "description": "Video segment where a label was detected.",
          "$ref": "GoogleCloudVideointelligenceV1_VideoSegment"
        }
      },
      "description": "Video segment level annotation results for label detection.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse": {
      "properties": {
        "annotationResults": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults"
          },
          "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.",
          "type": "array"
        }
      },
      "type": "object",
      "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoResponse"
    },
    "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame": {
      "properties": {
        "timeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location."
        },
        "pornographyLikelihood": {
          "enumDescriptions": [
            "Unspecified likelihood.",
            "Very unlikely.",
            "Unlikely.",
            "Possible.",
            "Likely.",
            "Very likely."
          ],
          "type": "string",
          "enum": [
            "LIKELIHOOD_UNSPECIFIED",
            "VERY_UNLIKELY",
            "UNLIKELY",
            "POSSIBLE",
            "LIKELY",
            "VERY_LIKELY"
          ],
          "description": "Likelihood of the pornography content.."
        }
      },
      "type": "object",
      "description": "Video frame level annotation results for explicit content.",
      "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame"
    },
    "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress": {
      "properties": {
        "progressPercent": {
          "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.",
          "format": "int32",
          "type": "integer"
        },
        "exportStatus": {
          "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request.",
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExportToOutputUriStatus"
        },
        "feature": {
          "enumDescriptions": [
            "Unspecified.",
            "Label detection. Detect objects, such as dog or flower.",
            "Shot change detection.",
            "Explicit content detection.",
            "Human face detection.",
            "Speech transcription.",
            "OCR text detection and tracking.",
            "Object detection and tracking.",
            "Logo detection, tracking, and recognition.",
            "Celebrity recognition.",
            "Person detection."
          ],
          "type": "string",
          "enum": [
            "FEATURE_UNSPECIFIED",
            "LABEL_DETECTION",
            "SHOT_CHANGE_DETECTION",
            "EXPLICIT_CONTENT_DETECTION",
            "FACE_DETECTION",
            "SPEECH_TRANSCRIPTION",
            "TEXT_DETECTION",
            "OBJECT_TRACKING",
            "LOGO_RECOGNITION",
            "CELEBRITY_RECOGNITION",
            "PERSON_DETECTION"
          ],
          "description": "Specifies which feature is being tracked if the request contains more than one feature."
        },
        "inputUri": {
          "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).",
          "type": "string"
        },
        "updateTime": {
          "format": "google-datetime",
          "type": "string",
          "description": "Time of the most recent update."
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment",
          "description": "Specifies which segment is being tracked if the request contains more than one segment."
        },
        "startTime": {
          "format": "google-datetime",
          "description": "Time when the request was received.",
          "type": "string"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationProgress",
      "description": "Annotation progress for a single video.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation": {
      "description": "Label annotation.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation",
      "properties": {
        "categoryEntities": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity"
          },
          "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`."
        },
        "version": {
          "type": "string",
          "description": "Feature version."
        },
        "segments": {
          "description": "All video segments where a label was detected.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment"
          }
        },
        "entity": {
          "description": "Detected entity.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity"
        },
        "frames": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame"
          },
          "type": "array",
          "description": "All video frames where a label was detected."
        }
      },
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1beta2_FaceAnnotation": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_FaceAnnotation",
      "properties": {
        "frames": {
          "description": "All video frames where a face was detected.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_FaceFrame"
          }
        },
        "segments": {
          "description": "All video segments where a face was detected.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_FaceSegment"
          },
          "type": "array"
        },
        "thumbnail": {
          "description": "Thumbnail of a representative face view (in JPEG format).",
          "type": "string",
          "format": "byte"
        }
      },
      "description": "Deprecated. No effect.",
      "deprecated": true
    },
    "GoogleCloudVideointelligenceV1_DetectedLandmark": {
      "type": "object",
      "description": "A generic detected landmark represented by name in string format and a 2D location.",
      "id": "GoogleCloudVideointelligenceV1_DetectedLandmark",
      "properties": {
        "confidence": {
          "description": "The confidence score of the detected landmark. Range [0, 1].",
          "type": "number",
          "format": "float"
        },
        "point": {
          "$ref": "GoogleCloudVideointelligenceV1_NormalizedVertex",
          "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1."
        },
        "name": {
          "type": "string",
          "description": "The name of this landmark, for example, left_hand, right_shoulder."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_TextSegment": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p1beta1_TextSegment",
      "description": "Video segment level annotation results for text detection.",
      "properties": {
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment",
          "description": "Video segment where a text snippet was detected."
        },
        "frames": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextFrame"
          },
          "description": "Information related to the frames where OCR detected text appears."
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Confidence for the track of detected text. It is calculated as the highest over all frames where OCR detected text appears."
        }
      }
    },
    "GoogleCloudVideointelligenceV1_NormalizedBoundingBox": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1_NormalizedBoundingBox",
      "properties": {
        "top": {
          "format": "float",
          "description": "Top Y coordinate.",
          "type": "number"
        },
        "bottom": {
          "type": "number",
          "description": "Bottom Y coordinate.",
          "format": "float"
        },
        "left": {
          "format": "float",
          "type": "number",
          "description": "Left X coordinate."
        },
        "right": {
          "format": "float",
          "description": "Right X coordinate.",
          "type": "number"
        }
      },
      "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1]."
    },
    "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation": {
      "description": "Annotations corresponding to one tracked object.",
      "id": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation",
      "properties": {
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "entity": {
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_Entity",
          "description": "Entity to specify the object category that this track is labeled as."
        },
        "frames": {
          "type": "array",
          "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingFrame"
          }
        },
        "segment": {
          "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.",
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment"
        },
        "confidence": {
          "description": "Object category's labeling confidence of this track.",
          "format": "float",
          "type": "number"
        },
        "trackId": {
          "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time.",
          "type": "string",
          "format": "int64"
        }
      },
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative": {
      "id": "GoogleCloudVideointelligenceV1p1beta1_SpeechRecognitionAlternative",
      "description": "Alternative hypotheses (a.k.a. n-best list).",
      "type": "object",
      "properties": {
        "confidence": {
          "type": "number",
          "format": "float",
          "readOnly": true,
          "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set."
        },
        "words": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_WordInfo"
          },
          "readOnly": true,
          "type": "array",
          "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio."
        },
        "transcript": {
          "description": "Transcript text representing the words that the user spoke.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_Entity": {
      "type": "object",
      "description": "Detected entity from video analysis.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_Entity",
      "properties": {
        "description": {
          "description": "Textual description, e.g., `Fixed-gear bicycle`.",
          "type": "string"
        },
        "languageCode": {
          "type": "string",
          "description": "Language code for `description` in BCP-47 format."
        },
        "entityId": {
          "type": "string",
          "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/)."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_RecognizedCelebrity",
      "description": "The recognized celebrity with confidence score.",
      "properties": {
        "celebrity": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_Celebrity",
          "description": "The recognized celebrity."
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Recognition confidence. Range [0, 1]."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_LabelSegment": {
      "type": "object",
      "description": "Video segment level annotation results for label detection.",
      "properties": {
        "confidence": {
          "description": "Confidence that the label is accurate. Range: [0, 1].",
          "format": "float",
          "type": "number"
        },
        "segment": {
          "description": "Video segment where a label was detected.",
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p1beta1_LabelSegment"
    },
    "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly": {
      "description": "Normalized bounding polygon for text (that might not be aligned with axis). Contains list of the corner points in clockwise order starting from top-left corner. For example, for a rectangular bounding box: When the text is horizontal it might look like: 0----1 | | 3----2 When it's clockwise rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertex order will still be (0, 1, 2, 3). Note that values can be less than 0, or greater than 1 due to trigonometric calculations for location of the box.",
      "id": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly",
      "type": "object",
      "properties": {
        "vertices": {
          "description": "Normalized vertices of the bounding polygon.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex"
          }
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation": {
      "id": "GoogleCloudVideointelligenceV1p3beta1_PersonDetectionAnnotation",
      "properties": {
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "tracks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_Track"
          },
          "description": "The detected tracks of a person.",
          "type": "array"
        }
      },
      "type": "object",
      "description": "Person detection annotation per video."
    },
    "GoogleCloudVideointelligenceV1p2beta1_TextDetectionConfig": {
      "properties": {
        "model": {
          "type": "string",
          "description": "Model to use for text detection. Supported values: \"builtin/stable\" (the default if unset) and \"builtin/latest\"."
        },
        "languageHints": {
          "description": "Language hint can be specified if the language to be detected is known a priori. It can increase the accuracy of the detection. Language hint must be language code in BCP-47 format. Automatic language detection is performed if no hint is provided.",
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "description": "Config for TEXT_DETECTION.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p2beta1_TextDetectionConfig"
    },
    "GoogleCloudVideointelligenceV1_TextAnnotation": {
      "type": "object",
      "properties": {
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "segments": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_TextSegment"
          },
          "description": "All video segments where OCR detected text appears.",
          "type": "array"
        },
        "text": {
          "description": "The detected text.",
          "type": "string"
        }
      },
      "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.",
      "id": "GoogleCloudVideointelligenceV1_TextAnnotation"
    },
    "GoogleCloudVideointelligenceV1beta2_LabelFrame": {
      "id": "GoogleCloudVideointelligenceV1beta2_LabelFrame",
      "type": "object",
      "description": "Video frame level annotation results for label detection.",
      "properties": {
        "timeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location."
        },
        "confidence": {
          "type": "number",
          "description": "Confidence that the label is accurate. Range: [0, 1].",
          "format": "float"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation": {
      "type": "object",
      "description": "Person detection annotation per video.",
      "properties": {
        "tracks": {
          "description": "The detected tracks of a person.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track"
          },
          "type": "array"
        },
        "version": {
          "type": "string",
          "description": "Feature version."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation"
    },
    "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults": {
      "properties": {
        "labelAnnotations": {
          "description": "Label annotation results.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation"
          }
        },
        "objectAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation"
          },
          "description": "Object tracking results."
        },
        "frameTimestamp": {
          "format": "google-duration",
          "type": "string",
          "description": "Timestamp of the processed frame in microseconds."
        },
        "shotAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment"
          },
          "description": "Shot annotation results. Each shot is represented as a video segment.",
          "type": "array"
        },
        "explicitAnnotation": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_ExplicitContentAnnotation",
          "description": "Explicit content annotation results."
        }
      },
      "description": "Streaming annotation results corresponding to a portion of the video that is currently being processed. Only ONE type of annotation will be specified in the response.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_StreamingVideoAnnotationResults"
    },
    "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame": {
      "properties": {
        "timeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "The timestamp of the frame in microseconds."
        },
        "normalizedBoundingBox": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox",
          "description": "The normalized bounding box location of this object track for the frame."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame",
      "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationProgress",
      "type": "object",
      "description": "Annotation progress for a single video.",
      "properties": {
        "feature": {
          "enumDescriptions": [
            "Unspecified.",
            "Label detection. Detect objects, such as dog or flower.",
            "Shot change detection.",
            "Explicit content detection.",
            "Human face detection.",
            "Speech transcription.",
            "OCR text detection and tracking.",
            "Object detection and tracking.",
            "Logo detection, tracking, and recognition.",
            "Person detection."
          ],
          "description": "Specifies which feature is being tracked if the request contains more than one feature.",
          "type": "string",
          "enum": [
            "FEATURE_UNSPECIFIED",
            "LABEL_DETECTION",
            "SHOT_CHANGE_DETECTION",
            "EXPLICIT_CONTENT_DETECTION",
            "FACE_DETECTION",
            "SPEECH_TRANSCRIPTION",
            "TEXT_DETECTION",
            "OBJECT_TRACKING",
            "LOGO_RECOGNITION",
            "PERSON_DETECTION"
          ]
        },
        "startTime": {
          "type": "string",
          "description": "Time when the request was received.",
          "format": "google-datetime"
        },
        "inputUri": {
          "type": "string",
          "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)."
        },
        "exportStatus": {
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExportToOutputUriStatus",
          "description": "Status of exporting annotation response to user specified `output_uri`. Only set if `output_uri` is set in the request."
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment",
          "description": "Specifies which segment is being tracked if the request contains more than one segment."
        },
        "progressPercent": {
          "description": "Approximate percentage processed thus far. Guaranteed to be 100 when fully processed.",
          "format": "int32",
          "type": "integer"
        },
        "updateTime": {
          "format": "google-datetime",
          "description": "Time of the most recent update.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation": {
      "id": "GoogleCloudVideointelligenceV1_PersonDetectionAnnotation",
      "type": "object",
      "description": "Person detection annotation per video.",
      "properties": {
        "version": {
          "type": "string",
          "description": "Feature version."
        },
        "tracks": {
          "type": "array",
          "description": "The detected tracks of a person.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_Track"
          }
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_Celebrity": {
      "description": "Celebrity definition.",
      "id": "GoogleCloudVideointelligenceV1p3beta1_Celebrity",
      "properties": {
        "displayName": {
          "description": "The celebrity name.",
          "type": "string"
        },
        "name": {
          "type": "string",
          "description": "The resource name of the celebrity. Have the format `video-intelligence/kg-mid` indicates a celebrity from preloaded gallery. kg-mid is the id in Google knowledge graph, which is unique for the celebrity."
        },
        "description": {
          "type": "string",
          "description": "Textual description of additional information about the celebrity, if applicable."
        }
      },
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1_TextFrame": {
      "properties": {
        "rotatedBoundingBox": {
          "$ref": "GoogleCloudVideointelligenceV1_NormalizedBoundingPoly",
          "description": "Bounding polygon of the detected text for this frame."
        },
        "timeOffset": {
          "format": "google-duration",
          "type": "string",
          "description": "Timestamp of this frame."
        }
      },
      "id": "GoogleCloudVideointelligenceV1_TextFrame",
      "type": "object",
      "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets."
    },
    "GoogleCloudVideointelligenceV1beta2_TextAnnotation": {
      "properties": {
        "segments": {
          "type": "array",
          "description": "All video segments where OCR detected text appears.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_TextSegment"
          }
        },
        "text": {
          "description": "The detected text.",
          "type": "string"
        },
        "version": {
          "type": "string",
          "description": "Feature version."
        }
      },
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_TextAnnotation",
      "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection."
    },
    "GoogleCloudVideointelligenceV1p1beta1_VideoSegment": {
      "description": "Video segment.",
      "type": "object",
      "properties": {
        "endTimeOffset": {
          "type": "string",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).",
          "format": "google-duration"
        },
        "startTimeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive)."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment"
    },
    "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_VideoAnnotationResults",
      "description": "Annotation results for a single video.",
      "type": "object",
      "properties": {
        "logoRecognitionAnnotations": {
          "type": "array",
          "description": "Annotations for list of logos detected, tracked and recognized in video.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation"
          }
        },
        "shotPresenceLabelAnnotations": {
          "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation"
          }
        },
        "personDetectionAnnotations": {
          "description": "Person detection annotations.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_PersonDetectionAnnotation"
          }
        },
        "speechTranscriptions": {
          "type": "array",
          "description": "Speech transcription.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription"
          }
        },
        "shotLabelAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation"
          },
          "description": "Topical label annotations on shot level. There is exactly one element for each unique label."
        },
        "frameLabelAnnotations": {
          "description": "Label annotations on frame level. There is exactly one element for each unique label.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation"
          }
        },
        "faceDetectionAnnotations": {
          "description": "Face detection annotations.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceDetectionAnnotation"
          },
          "type": "array"
        },
        "faceAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation"
          },
          "type": "array",
          "deprecated": true,
          "description": "Deprecated. Please use `face_detection_annotations` instead."
        },
        "textAnnotations": {
          "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation"
          }
        },
        "segmentPresenceLabelAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation"
          },
          "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
          "type": "array"
        },
        "explicitAnnotation": {
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation",
          "description": "Explicit content annotation."
        },
        "segment": {
          "description": "Video segment on which the annotation is run.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment"
        },
        "inputUri": {
          "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/).",
          "type": "string"
        },
        "segmentLabelAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_LabelAnnotation"
          },
          "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label."
        },
        "objectAnnotations": {
          "description": "Annotations for list of objects detected and tracked in video.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation"
          },
          "type": "array"
        },
        "shotAnnotations": {
          "description": "Shot annotations. Each shot is represented as a video segment.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment"
          }
        },
        "error": {
          "$ref": "GoogleRpc_Status",
          "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail."
        }
      }
    },
    "GoogleCloudVideointelligenceV1beta2_NormalizedVertex": {
      "type": "object",
      "properties": {
        "y": {
          "type": "number",
          "format": "float",
          "description": "Y coordinate."
        },
        "x": {
          "format": "float",
          "description": "X coordinate.",
          "type": "number"
        }
      },
      "id": "GoogleCloudVideointelligenceV1beta2_NormalizedVertex",
      "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1."
    },
    "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation": {
      "description": "Deprecated. No effect.",
      "id": "GoogleCloudVideointelligenceV1p3beta1_FaceAnnotation",
      "properties": {
        "frames": {
          "description": "All video frames where a face was detected.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceFrame"
          }
        },
        "thumbnail": {
          "format": "byte",
          "type": "string",
          "description": "Thumbnail of a representative face view (in JPEG format)."
        },
        "segments": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_FaceSegment"
          },
          "description": "All video segments where a face was detected.",
          "type": "array"
        }
      },
      "type": "object",
      "deprecated": true
    },
    "GoogleCloudVideointelligenceV1p1beta1_Entity": {
      "properties": {
        "languageCode": {
          "type": "string",
          "description": "Language code for `description` in BCP-47 format."
        },
        "description": {
          "description": "Textual description, e.g., `Fixed-gear bicycle`.",
          "type": "string"
        },
        "entityId": {
          "type": "string",
          "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/)."
        }
      },
      "description": "Detected entity from video analysis.",
      "id": "GoogleCloudVideointelligenceV1p1beta1_Entity",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p1beta1_TextFrame": {
      "id": "GoogleCloudVideointelligenceV1p1beta1_TextFrame",
      "properties": {
        "rotatedBoundingBox": {
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingPoly",
          "description": "Bounding polygon of the detected text for this frame."
        },
        "timeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "Timestamp of this frame."
        }
      },
      "type": "object",
      "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets."
    },
    "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription": {
      "description": "A speech recognition result corresponding to a portion of the audio.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p2beta1_SpeechTranscription",
      "properties": {
        "alternatives": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_SpeechRecognitionAlternative"
          },
          "description": "May contain one or more recognition hypotheses (up to the maximum specified in `max_alternatives`). These alternatives are ordered in terms of accuracy, with the top (first) alternative being the most probable, as ranked by the recognizer."
        },
        "languageCode": {
          "readOnly": true,
          "description": "Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag of the language in this result. This language code was detected to have the most likelihood of being spoken in the audio.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_FaceSegment": {
      "type": "object",
      "properties": {
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment",
          "description": "Video segment where a face was detected."
        }
      },
      "description": "Video segment level annotation results for face detection.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_FaceSegment"
    },
    "GoogleCloudVideointelligenceV1p2beta1_ShotChangeDetectionConfig": {
      "type": "object",
      "properties": {
        "model": {
          "description": "Model to use for shot change detection. Supported values: \"builtin/stable\" (the default if unset), \"builtin/latest\", and \"builtin/legacy\".",
          "type": "string"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_ShotChangeDetectionConfig",
      "description": "Config for SHOT_CHANGE_DETECTION."
    },
    "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse": {
      "type": "object",
      "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
      "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoResponse",
      "properties": {
        "annotationResults": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults"
          },
          "type": "array",
          "description": "Annotation results for all videos specified in `AnnotateVideoRequest`."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation": {
      "id": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation",
      "type": "object",
      "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.",
      "properties": {
        "text": {
          "description": "The detected text.",
          "type": "string"
        },
        "version": {
          "type": "string",
          "description": "Feature version."
        },
        "segments": {
          "type": "array",
          "description": "All video segments where OCR detected text appears.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextSegment"
          }
        }
      }
    },
    "GoogleCloudVideointelligenceV1_DetectedAttribute": {
      "id": "GoogleCloudVideointelligenceV1_DetectedAttribute",
      "description": "A generic detected attribute represented by name in string format.",
      "type": "object",
      "properties": {
        "value": {
          "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.",
          "type": "string"
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Detected attribute confidence. Range [0, 1]."
        },
        "name": {
          "type": "string",
          "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress": {
      "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p1beta1_AnnotateVideoProgress",
      "properties": {
        "annotationProgress": {
          "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationProgress"
          }
        }
      }
    },
    "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation": {
      "properties": {
        "tracks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_Track"
          },
          "type": "array",
          "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames."
        },
        "entity": {
          "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_Entity"
        },
        "segments": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment"
          },
          "type": "array",
          "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment."
        }
      },
      "description": "Annotation corresponding to one detected, tracked and recognized logo class.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_LogoRecognitionAnnotation"
    },
    "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation": {
      "id": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingAnnotation",
      "type": "object",
      "description": "Annotations corresponding to one tracked object.",
      "properties": {
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Object category's labeling confidence of this track."
        },
        "segment": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoSegment",
          "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears."
        },
        "entity": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity",
          "description": "Entity to specify the object category that this track is labeled as."
        },
        "frames": {
          "type": "array",
          "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_ObjectTrackingFrame"
          }
        },
        "trackId": {
          "type": "string",
          "format": "int64",
          "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark",
      "description": "A generic detected landmark represented by name in string format and a 2D location.",
      "properties": {
        "point": {
          "description": "The 2D point of the detected landmark using the normalized image coordinate system. The normalized coordinates have the range from 0 to 1.",
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex"
        },
        "name": {
          "type": "string",
          "description": "The name of this landmark, for example, left_hand, right_shoulder."
        },
        "confidence": {
          "description": "The confidence score of the detected landmark. Range [0, 1].",
          "type": "number",
          "format": "float"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox": {
      "properties": {
        "bottom": {
          "format": "float",
          "type": "number",
          "description": "Bottom Y coordinate."
        },
        "right": {
          "description": "Right X coordinate.",
          "format": "float",
          "type": "number"
        },
        "left": {
          "format": "float",
          "description": "Left X coordinate.",
          "type": "number"
        },
        "top": {
          "format": "float",
          "description": "Top Y coordinate.",
          "type": "number"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox",
      "type": "object",
      "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1]."
    },
    "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedBoundingBox",
      "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].",
      "properties": {
        "bottom": {
          "description": "Bottom Y coordinate.",
          "type": "number",
          "format": "float"
        },
        "top": {
          "description": "Top Y coordinate.",
          "format": "float",
          "type": "number"
        },
        "left": {
          "format": "float",
          "type": "number",
          "description": "Left X coordinate."
        },
        "right": {
          "format": "float",
          "description": "Right X coordinate.",
          "type": "number"
        }
      },
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex": {
      "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.",
      "id": "GoogleCloudVideointelligenceV1p1beta1_NormalizedVertex",
      "type": "object",
      "properties": {
        "y": {
          "description": "Y coordinate.",
          "type": "number",
          "format": "float"
        },
        "x": {
          "description": "X coordinate.",
          "format": "float",
          "type": "number"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_LabelFrame": {
      "description": "Video frame level annotation results for label detection.",
      "properties": {
        "timeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location."
        },
        "confidence": {
          "description": "Confidence that the label is accurate. Range: [0, 1].",
          "format": "float",
          "type": "number"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_LabelFrame",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation": {
      "properties": {
        "entity": {
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity",
          "description": "Entity category information to specify the logo class that all the logo tracks within this LogoRecognitionAnnotation are recognized as."
        },
        "segments": {
          "description": "All video segments where the recognized logo appears. There might be multiple instances of the same logo class appearing in one VideoSegment.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment"
          },
          "type": "array"
        },
        "tracks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_Track"
          },
          "type": "array",
          "description": "All logo tracks where the recognized logo appears. Each track corresponds to one logo instance appearing in consecutive frames."
        }
      },
      "description": "Annotation corresponding to one detected, tracked and recognized logo class.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p2beta1_LogoRecognitionAnnotation"
    },
    "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress": {
      "description": "Video annotation progress. Included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
      "id": "GoogleCloudVideointelligenceV1beta2_AnnotateVideoProgress",
      "properties": {
        "annotationProgress": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_VideoAnnotationProgress"
          },
          "description": "Progress metadata for all videos specified in `AnnotateVideoRequest`."
        }
      },
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1beta2_Entity": {
      "properties": {
        "entityId": {
          "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).",
          "type": "string"
        },
        "description": {
          "type": "string",
          "description": "Textual description, e.g., `Fixed-gear bicycle`."
        },
        "languageCode": {
          "type": "string",
          "description": "Language code for `description` in BCP-47 format."
        }
      },
      "description": "Detected entity from video analysis.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1beta2_Entity"
    },
    "GoogleCloudVideointelligenceV1p2beta1_LabelSegment": {
      "type": "object",
      "description": "Video segment level annotation results for label detection.",
      "id": "GoogleCloudVideointelligenceV1p2beta1_LabelSegment",
      "properties": {
        "segment": {
          "description": "Video segment where a label was detected.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment"
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Confidence that the label is accurate. Range: [0, 1]."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p1beta1_FaceFrame": {
      "description": "Deprecated. No effect.",
      "properties": {
        "normalizedBoundingBoxes": {
          "description": "Normalized Bounding boxes in a frame. There can be more than one boxes if the same face is detected in multiple locations within the current frame.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox"
          },
          "type": "array"
        },
        "timeOffset": {
          "type": "string",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location.",
          "format": "google-duration"
        }
      },
      "type": "object",
      "deprecated": true,
      "id": "GoogleCloudVideointelligenceV1p1beta1_FaceFrame"
    },
    "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject": {
      "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p1beta1_TimestampedObject",
      "properties": {
        "normalizedBoundingBox": {
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_NormalizedBoundingBox",
          "description": "Normalized Bounding box in a frame, where the object is located."
        },
        "timeOffset": {
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.",
          "format": "google-duration",
          "type": "string"
        },
        "landmarks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedLandmark"
          },
          "type": "array",
          "description": "Optional. The detected landmarks."
        },
        "attributes": {
          "description": "Optional. The attributes of the object in the bounding box.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_DetectedAttribute"
          },
          "type": "array"
        }
      }
    },
    "GoogleCloudVideointelligenceV1beta2_FaceSegment": {
      "description": "Video segment level annotation results for face detection.",
      "type": "object",
      "properties": {
        "segment": {
          "description": "Video segment where a face was detected.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_VideoSegment"
        }
      },
      "id": "GoogleCloudVideointelligenceV1beta2_FaceSegment"
    },
    "GoogleCloudVideointelligenceV1beta2_TextFrame": {
      "properties": {
        "rotatedBoundingBox": {
          "description": "Bounding polygon of the detected text for this frame.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingPoly"
        },
        "timeOffset": {
          "format": "google-duration",
          "type": "string",
          "description": "Timestamp of this frame."
        }
      },
      "description": "Video frame level annotation results for text annotation (OCR). Contains information regarding timestamp and bounding box locations for the frames containing detected OCR text snippets.",
      "id": "GoogleCloudVideointelligenceV1beta2_TextFrame",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p3beta1_LabelFrame": {
      "type": "object",
      "description": "Video frame level annotation results for label detection.",
      "properties": {
        "timeOffset": {
          "format": "google-duration",
          "type": "string",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location."
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Confidence that the label is accurate. Range: [0, 1]."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p3beta1_LabelFrame"
    },
    "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation": {
      "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_TextAnnotation",
      "properties": {
        "text": {
          "description": "The detected text.",
          "type": "string"
        },
        "version": {
          "type": "string",
          "description": "Feature version."
        },
        "segments": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_TextSegment"
          },
          "type": "array",
          "description": "All video segments where OCR detected text appears."
        }
      }
    },
    "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoResponse": {
      "id": "GoogleCloudVideointelligenceV1p3beta1_AnnotateVideoResponse",
      "description": "Video annotation response. Included in the `response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
      "properties": {
        "annotationResults": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_VideoAnnotationResults"
          },
          "description": "Annotation results for all videos specified in `AnnotateVideoRequest`.",
          "type": "array"
        }
      },
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1beta2_TimestampedObject": {
      "properties": {
        "normalizedBoundingBox": {
          "description": "Normalized Bounding box in a frame, where the object is located.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox"
        },
        "attributes": {
          "description": "Optional. The attributes of the object in the bounding box.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedAttribute"
          },
          "type": "array"
        },
        "timeOffset": {
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this object.",
          "type": "string",
          "format": "google-duration"
        },
        "landmarks": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1beta2_DetectedLandmark"
          },
          "description": "Optional. The detected landmarks.",
          "type": "array"
        }
      },
      "id": "GoogleCloudVideointelligenceV1beta2_TimestampedObject",
      "type": "object",
      "description": "For tracking related features. An object at time_offset with attributes, and located with normalized_bounding_box."
    },
    "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_TextAnnotation",
      "properties": {
        "text": {
          "description": "The detected text.",
          "type": "string"
        },
        "segments": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_TextSegment"
          },
          "description": "All video segments where OCR detected text appears."
        },
        "version": {
          "description": "Feature version.",
          "type": "string"
        }
      },
      "description": "Annotations related to one detected OCR text snippet. This will contain the corresponding text, confidence value, and frame level information for each detection.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox": {
      "description": "Normalized bounding box. The normalized vertex coordinates are relative to the original image. Range: [0, 1].",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p3beta1_NormalizedBoundingBox",
      "properties": {
        "bottom": {
          "type": "number",
          "format": "float",
          "description": "Bottom Y coordinate."
        },
        "right": {
          "format": "float",
          "type": "number",
          "description": "Right X coordinate."
        },
        "left": {
          "type": "number",
          "description": "Left X coordinate.",
          "format": "float"
        },
        "top": {
          "type": "number",
          "description": "Top Y coordinate.",
          "format": "float"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_VideoSegment": {
      "properties": {
        "startTimeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the start of the segment (inclusive)."
        },
        "endTimeOffset": {
          "description": "Time-offset, relative to the beginning of the video, corresponding to the end of the segment (inclusive).",
          "type": "string",
          "format": "google-duration"
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment",
      "type": "object",
      "description": "Video segment."
    },
    "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus": {
      "description": "Status of exporting annotation response to user specified `output_uri`.",
      "properties": {
        "state": {
          "description": "Output only. State of the `output_uri` export.",
          "enumDescriptions": [
            "Default value.",
            "Export succeeded.",
            "Export failed."
          ],
          "type": "string",
          "enum": [
            "STATE_UNSPECIFIED",
            "SUCCEEDED",
            "FAILED"
          ],
          "readOnly": true
        },
        "status": {
          "$ref": "GoogleRpc_Status",
          "readOnly": true,
          "description": "Output only. Only set if state is FAILED."
        }
      },
      "id": "GoogleCloudVideointelligenceV1_ExportToOutputUriStatus",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation": {
      "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame.",
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation",
      "properties": {
        "frames": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentFrame"
          },
          "description": "All video frames where explicit content was detected."
        },
        "version": {
          "description": "Feature version.",
          "type": "string"
        }
      }
    },
    "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation": {
      "properties": {
        "version": {
          "type": "string",
          "description": "Feature version."
        },
        "entity": {
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_Entity",
          "description": "Entity to specify the object category that this track is labeled as."
        },
        "frames": {
          "description": "Information corresponding to all frames where this object track appears. Non-streaming batch mode: it may be one or multiple ObjectTrackingFrame messages in frames. Streaming mode: it can only be one ObjectTrackingFrame message in frames.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingFrame"
          }
        },
        "confidence": {
          "description": "Object category's labeling confidence of this track.",
          "type": "number",
          "format": "float"
        },
        "segment": {
          "description": "Non-streaming batch mode ONLY. Each object track corresponds to one video segment where it appears.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment"
        },
        "trackId": {
          "type": "string",
          "format": "int64",
          "description": "Streaming mode ONLY. In streaming mode, we do not know the end time of a tracked object before it is completed. Hence, there is no VideoSegment info returned. Instead, we provide a unique identifiable integer track_id so that the customers can correlate the results of the ongoing ObjectTrackAnnotation of the same track_id over time."
        }
      },
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1p2beta1_ObjectTrackingAnnotation",
      "description": "Annotations corresponding to one tracked object."
    },
    "GoogleCloudVideointelligenceV1p2beta1_Track": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_Track",
      "properties": {
        "segment": {
          "description": "Video segment of a track.",
          "$ref": "GoogleCloudVideointelligenceV1p2beta1_VideoSegment"
        },
        "attributes": {
          "type": "array",
          "description": "Optional. Attributes in the track level.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_DetectedAttribute"
          }
        },
        "confidence": {
          "type": "number",
          "description": "Optional. The confidence score of the tracked object.",
          "format": "float"
        },
        "timestampedObjects": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_TimestampedObject"
          },
          "description": "The object with timestamp and attributes per frame in the track.",
          "type": "array"
        }
      },
      "type": "object",
      "description": "A track of an object instance."
    },
    "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation": {
      "deprecated": true,
      "properties": {
        "thumbnail": {
          "description": "Thumbnail of a representative face view (in JPEG format).",
          "format": "byte",
          "type": "string"
        },
        "segments": {
          "type": "array",
          "description": "All video segments where a face was detected.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceSegment"
          }
        },
        "frames": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_FaceFrame"
          },
          "type": "array",
          "description": "All video frames where a face was detected."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_FaceAnnotation",
      "description": "Deprecated. No effect.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative": {
      "properties": {
        "transcript": {
          "type": "string",
          "description": "Transcript text representing the words that the user spoke."
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Output only. The confidence estimate between 0.0 and 1.0. A higher number indicates an estimated greater likelihood that the recognized words are correct. This field is set only for the top alternative. This field is not guaranteed to be accurate and users should not rely on it to be always provided. The default of 0.0 is a sentinel value indicating `confidence` was not set.",
          "readOnly": true
        },
        "words": {
          "type": "array",
          "description": "Output only. A list of word-specific information for each recognized word. Note: When `enable_speaker_diarization` is set to true, you will see all the words from the beginning of the audio.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_WordInfo"
          },
          "readOnly": true
        }
      },
      "id": "GoogleCloudVideointelligenceV1_SpeechRecognitionAlternative",
      "type": "object",
      "description": "Alternative hypotheses (a.k.a. n-best list)."
    },
    "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation": {
      "properties": {
        "version": {
          "type": "string",
          "description": "Feature version."
        },
        "frames": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentFrame"
          },
          "type": "array",
          "description": "All video frames where explicit content was detected."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p2beta1_ExplicitContentAnnotation",
      "type": "object",
      "description": "Explicit content annotation (based on per-frame visual signals only). If no explicit content has been detected in a frame, no annotations are present for that frame."
    },
    "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame": {
      "id": "GoogleCloudVideointelligenceV1beta2_ExplicitContentFrame",
      "properties": {
        "pornographyLikelihood": {
          "enumDescriptions": [
            "Unspecified likelihood.",
            "Very unlikely.",
            "Unlikely.",
            "Possible.",
            "Likely.",
            "Very likely."
          ],
          "type": "string",
          "enum": [
            "LIKELIHOOD_UNSPECIFIED",
            "VERY_UNLIKELY",
            "UNLIKELY",
            "POSSIBLE",
            "LIKELY",
            "VERY_LIKELY"
          ],
          "description": "Likelihood of the pornography content.."
        },
        "timeOffset": {
          "format": "google-duration",
          "type": "string",
          "description": "Time-offset, relative to the beginning of the video, corresponding to the video frame for this location."
        }
      },
      "type": "object",
      "description": "Video frame level annotation results for explicit content."
    },
    "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation": {
      "type": "object",
      "properties": {
        "segments": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelSegment"
          },
          "type": "array",
          "description": "All video segments where a label was detected."
        },
        "entity": {
          "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity",
          "description": "Detected entity."
        },
        "frames": {
          "description": "All video frames where a label was detected.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_LabelFrame"
          }
        },
        "version": {
          "description": "Feature version.",
          "type": "string"
        },
        "categoryEntities": {
          "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p3beta1_Entity"
          }
        }
      },
      "id": "GoogleCloudVideointelligenceV1p3beta1_LabelAnnotation",
      "description": "Label annotation."
    },
    "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex": {
      "id": "GoogleCloudVideointelligenceV1p2beta1_NormalizedVertex",
      "properties": {
        "x": {
          "format": "float",
          "description": "X coordinate.",
          "type": "number"
        },
        "y": {
          "format": "float",
          "type": "number",
          "description": "Y coordinate."
        }
      },
      "type": "object",
      "description": "A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1."
    },
    "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults": {
      "id": "GoogleCloudVideointelligenceV1p1beta1_VideoAnnotationResults",
      "properties": {
        "objectAnnotations": {
          "description": "Annotations for list of objects detected and tracked in video.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_ObjectTrackingAnnotation"
          },
          "type": "array"
        },
        "frameLabelAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation"
          },
          "description": "Label annotations on frame level. There is exactly one element for each unique label."
        },
        "textAnnotations": {
          "description": "OCR text detection and tracking. Annotations for list of detected text snippets. Each will have list of frame information associated with it.",
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_TextAnnotation"
          }
        },
        "shotLabelAnnotations": {
          "description": "Topical label annotations on shot level. There is exactly one element for each unique label.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation"
          },
          "type": "array"
        },
        "shotAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment"
          },
          "type": "array",
          "description": "Shot annotations. Each shot is represented as a video segment."
        },
        "segmentLabelAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation"
          },
          "type": "array",
          "description": "Topical label annotations on video level or user-specified segment level. There is exactly one element for each unique label."
        },
        "speechTranscriptions": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_SpeechTranscription"
          },
          "type": "array",
          "description": "Speech transcription."
        },
        "error": {
          "$ref": "GoogleRpc_Status",
          "description": "If set, indicates an error. Note that for a single `AnnotateVideoRequest` some videos may succeed and some may fail."
        },
        "segmentPresenceLabelAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation"
          },
          "description": "Presence label annotations on video level or user-specified segment level. There is exactly one element for each unique label. Compared to the existing topical `segment_label_annotations`, this field presents more fine-grained, segment-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request."
        },
        "faceDetectionAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceDetectionAnnotation"
          },
          "description": "Face detection annotations."
        },
        "shotPresenceLabelAnnotations": {
          "description": "Presence label annotations on shot level. There is exactly one element for each unique label. Compared to the existing topical `shot_label_annotations`, this field presents more fine-grained, shot-level labels detected in video content and is made available only when the client sets `LabelDetectionConfig.model` to \"builtin/latest\" in the request.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_LabelAnnotation"
          },
          "type": "array"
        },
        "inputUri": {
          "type": "string",
          "description": "Video file location in [Cloud Storage](https://cloud.google.com/storage/)."
        },
        "faceAnnotations": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_FaceAnnotation"
          },
          "deprecated": true,
          "description": "Deprecated. Please use `face_detection_annotations` instead.",
          "type": "array"
        },
        "explicitAnnotation": {
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_ExplicitContentAnnotation",
          "description": "Explicit content annotation."
        },
        "personDetectionAnnotations": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_PersonDetectionAnnotation"
          },
          "description": "Person detection annotations."
        },
        "logoRecognitionAnnotations": {
          "description": "Annotations for list of logos detected, tracked and recognized in video.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1p1beta1_LogoRecognitionAnnotation"
          },
          "type": "array"
        },
        "segment": {
          "description": "Video segment on which the annotation is run.",
          "$ref": "GoogleCloudVideointelligenceV1p1beta1_VideoSegment"
        }
      },
      "description": "Annotation results for a single video.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1_Entity": {
      "properties": {
        "description": {
          "description": "Textual description, e.g., `Fixed-gear bicycle`.",
          "type": "string"
        },
        "languageCode": {
          "description": "Language code for `description` in BCP-47 format.",
          "type": "string"
        },
        "entityId": {
          "description": "Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).",
          "type": "string"
        }
      },
      "id": "GoogleCloudVideointelligenceV1_Entity",
      "description": "Detected entity from video analysis.",
      "type": "object"
    },
    "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame": {
      "type": "object",
      "description": "Video frame level annotations for object detection and tracking. This field stores per frame location, time offset, and confidence.",
      "id": "GoogleCloudVideointelligenceV1beta2_ObjectTrackingFrame",
      "properties": {
        "normalizedBoundingBox": {
          "description": "The normalized bounding box location of this object track for the frame.",
          "$ref": "GoogleCloudVideointelligenceV1beta2_NormalizedBoundingBox"
        },
        "timeOffset": {
          "type": "string",
          "format": "google-duration",
          "description": "The timestamp of the frame in microseconds."
        }
      }
    },
    "GoogleCloudVideointelligenceV1_LabelAnnotation": {
      "type": "object",
      "id": "GoogleCloudVideointelligenceV1_LabelAnnotation",
      "description": "Label annotation.",
      "properties": {
        "categoryEntities": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_Entity"
          },
          "description": "Common categories for the detected entity. For example, when the label is `Terrier`, the category is likely `dog`. And in some cases there might be more than one categories e.g., `Terrier` could also be a `pet`.",
          "type": "array"
        },
        "version": {
          "type": "string",
          "description": "Feature version."
        },
        "segments": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_LabelSegment"
          },
          "type": "array",
          "description": "All video segments where a label was detected."
        },
        "entity": {
          "description": "Detected entity.",
          "$ref": "GoogleCloudVideointelligenceV1_Entity"
        },
        "frames": {
          "type": "array",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_LabelFrame"
          },
          "description": "All video frames where a label was detected."
        }
      }
    },
    "GoogleCloudVideointelligenceV1_FaceAnnotation": {
      "type": "object",
      "properties": {
        "segments": {
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_FaceSegment"
          },
          "description": "All video segments where a face was detected.",
          "type": "array"
        },
        "thumbnail": {
          "type": "string",
          "description": "Thumbnail of a representative face view (in JPEG format).",
          "format": "byte"
        },
        "frames": {
          "description": "All video frames where a face was detected.",
          "items": {
            "$ref": "GoogleCloudVideointelligenceV1_FaceFrame"
          },
          "type": "array"
        }
      },
      "deprecated": true,
      "description": "Deprecated. No effect.",
      "id": "GoogleCloudVideointelligenceV1_FaceAnnotation"
    },
    "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute": {
      "description": "A generic detected attribute represented by name in string format.",
      "properties": {
        "value": {
          "description": "Text value of the detection result. For example, the value for \"HairColor\" can be \"black\", \"blonde\", etc.",
          "type": "string"
        },
        "confidence": {
          "format": "float",
          "type": "number",
          "description": "Detected attribute confidence. Range [0, 1]."
        },
        "name": {
          "type": "string",
          "description": "The name of the attribute, for example, glasses, dark_glasses, mouth_open. A full list of supported type names will be provided in the document."
        }
      },
      "id": "GoogleCloudVideointelligenceV1p3beta1_DetectedAttribute",
      "type": "object"
    }
  },
  "basePath": "",
  "description": "Detects objects, explicit content, and scene changes in videos. It also specifies the region for annotation and transcribes speech to text. Supports both asynchronous API and streaming API.",
  "resources": {
    "videos": {
      "methods": {
        "annotate": {
          "parameterOrder": [],
          "response": {
            "$ref": "GoogleLongrunning_Operation"
          },
          "scopes": [
            "https://www.googleapis.com/auth/cloud-platform"
          ],
          "description": "Performs asynchronous video annotation. Progress and results can be retrieved through the `google.longrunning.Operations` interface. `Operation.metadata` contains `AnnotateVideoProgress` (progress). `Operation.response` contains `AnnotateVideoResponse` (results).",
          "id": "videointelligence.videos.annotate",
          "httpMethod": "POST",
          "request": {
            "$ref": "GoogleCloudVideointelligenceV1p2beta1_AnnotateVideoRequest"
          },
          "parameters": {},
          "path": "v1p2beta1/videos:annotate",
          "flatPath": "v1p2beta1/videos:annotate"
        }
      }
    }
  },
  "ownerName": "Google",
  "mtlsRootUrl": "https://videointelligence.mtls.googleapis.com/",
  "version": "v1p2beta1",
  "kind": "discovery#restDescription",
  "auth": {
    "oauth2": {
      "scopes": {
        "https://www.googleapis.com/auth/cloud-platform": {
          "description": "See, edit, configure, and delete your Google Cloud data and see the email address for your Google Account."
        }
      }
    }
  },
  "protocol": "rest",
  "servicePath": "",
  "icons": {
    "x32": "http://www.google.com/images/icons/product/search-32.gif",
    "x16": "http://www.google.com/images/icons/product/search-16.gif"
  },
  "canonicalName": "Cloud Video Intelligence",
  "baseUrl": "https://videointelligence.googleapis.com/",
  "fullyEncodeReservedExpansion": true,
  "title": "Cloud Video Intelligence API",
  "ownerDomain": "google.com",
  "name": "videointelligence",
  "id": "videointelligence:v1p2beta1"
}
