ALEXANDRIA, Va., Dec. 2 -- United States Patent no. 12,488,620, issued on Dec. 2, was assigned to SOOCHOW UNIVERSITY (Suzhou, China).

"Spatiotemporal enhancement network based video action recognition method" was invented by He Huang (Suzhou, China) and Jianuo Yu (Suzhou, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "The invention provides a spatiotemporal enhancement network based video action recognition method, including: S1. equally partitioning a video into T time periods, and randomly sampling one frame from each time period, to obtain an input sequence with T frames of image; S2. preprocessing the image sequence acquired in S1; S3. taking a tensor obtained in S2 as an input, inputting the tenso...