Google Inc.

Arvind Balasubramanian

David A Ross

Sudheendra Vijayanarasimhan

Timothy Priestley Novikoff

Alexis Bienvenu

Arun Kumar Kandoor

Akhil Raju

A computer-implemented method includes receiving a video that includes multiple frames. The method further includes identifying a start time and an end time of each action in the video based on application of one or more of an audio classifier, an RGB classifier, and a motion classifier. The method further includes identifying video segments from the video that include frames between the start time and the end time for each action in the video. The method further includes generating a confidence score for each of the video segments based on a probability that a corresponding action corresponds to one or more of a set of predetermined actions. The method further includes selecting a subset of the video segments based on the confidence score for each of the video segments.

Generating a video segment of an action from a video

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating synthesis videos. In one aspect, a method comprises identifying one or more topics for generation of a synthesis video. Videos are identified that are determined to be relevant to one or more of the identified topics. Video segments are extracted from one or more of the identified videos. For each of the video segments, a segment level score and a video level score are determined. A composite score for the video segment is determined by combining the segment level score and the video level score for the video segment. Video segments are selected for inclusion in the synthesis video based on the composite scores for the video segments. A synthesis video is generated by combining the selected video segments.

Generating synthesis videos

Growing community of inventors

Fremont, CA, United States of America

Arvind Balasubramanian