ALEXANDRIA, Va., Sept. 24 -- United States Patent no. 12,743,884, issued on Sept. 22, was assigned to Honda Motor Co. Ltd. (Tokyo) and Brown University (Providence, R.I.).

"Versatile action models (Vamos) for video understanding" was invented by Shijie Wang (Providence, R.I.), Qi Zhao (Riverside, R.I.), Minh Quan Do (Providence, R.I.), Nakul Agarwal (San Francisco), Kwonjoon Lee (San Jose, Calif.) and Chen Sun (San Francisco).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for forming versatile action models for video understanding may gather data from a video. The data may comprise textual video representations and other task specific language inputs. The method may use a pre-trained large language m...