VideoActionRecognitionPredictionResult

Prediction output format for Video Action Recognition.

Fields
id string

The resource id of the AnnotationSpec that had been identified.

displayName string

The display name of the AnnotationSpec that had been identified.

timeSegmentStart string (Duration format)

The beginning, inclusive, of the video's time segment in which the AnnotationSpec has been identified. Expressed as a number of seconds as measured from the start of the video, with fractions up to a microsecond precision, and with "s" appended at the end.

A duration in seconds with up to nine fractional digits, ending with 's'. Example: "3.5s".

timeSegmentEnd string (Duration format)

The end, exclusive, of the video's time segment in which the AnnotationSpec has been identified. Expressed as a number of seconds as measured from the start of the video, with fractions up to a microsecond precision, and with "s" appended at the end.

A duration in seconds with up to nine fractional digits, ending with 's'. Example: "3.5s".

confidence number

The Model's confidence in correction of this prediction, higher value means higher confidence.

JSON representation 
{
  "id": string,
  "displayName": string,
  "timeSegmentStart": string,
  "timeSegmentEnd": string,
  "confidence": number
}