US Patent Issued on Sept. 2 for "Anticipative video transformer model for future action anticipation" (New Jersey, Texas Inventors)

ALEXANDRIA, Va., Sept. 3 -- United States Patent no. 12,406,496, issued on Sept. 2.

"Anticipative video transformer model for future action anticipation" was invented by Rohit Girdhar (Jersey City, N.J.) and Kristen Lorraine Grauman (Austin, Texas).

According to the abstract* released by the U.S. Patent & Trademark Office: "In particular embodiments, a computing system may receive a video comprising a plurality of image frames. The system may generate, for each image frame in the plurality of image frames and using a spatial-attention encoder, an image-frame feature corresponding to the image frame. For each image-frame feature, the system may generate, using a temporal-attention decoder, a predicted future feature based on one or more of...