Patent 10013640 was granted and assigned to Google on July, 2018 by the United States Patent and Trademark Office.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying an object from a video. One of the methods includes obtaining multiple frames from a video, where each frame of the multiple frames depicts an object to be recognized, and processing, using an object recognition model, the multiple frames to generate data that represents a classification of the object to be recognized.