Class VideoActionRecognitionPredictionResult (0.1.1)

VideoActionRecognitionPredictionResult(
    mapping=None, *, ignore_unknown_fields=False, **kwargs
)

Prediction output format for Video Action Recognition.

Attributes

Name Description
segment_start_time google.protobuf.timestamp_pb2.Timestamp
The beginning, inclusive, of the video's time segment in which the actions have been identified.
segment_end_time google.protobuf.timestamp_pb2.Timestamp
The end, inclusive, of the video's time segment in which the actions have been identified. Particularly, if the end is the same as the start, it means the identification happens on a specific video frame.
actions MutableSequence[google.cloud.visionai_v1.types.VideoActionRecognitionPredictionResult.IdentifiedAction]
All of the actions identified in the time range.

Classes

IdentifiedAction

IdentifiedAction(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Each IdentifiedAction is one particular identification of an action specified with the AnnotationSpec id, display_name and the associated confidence score.