US Patent Issued to TOYOTA RESEARCH INSTITUTE, TOYOTA JIDOSHA, The Regents of the University of California, THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOIS, CARNEGIE MELLON UNIVERSITY on June 30 for "Self-supervised compositional feature representation for video understanding" (American, Canadian Inventors)

ALEXANDRIA, Va., July 16 -- United States Patent no. 12,670,722, issued on June 30, was assigned to TOYOTA RESEARCH INSTITUTE INC., TOYOTA JIDOSHA K.K. (Aichi-Ken, Japan), The Regents of the University of California, THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOIS and CARNEGIE MELLON UNIVERSITY.

"Self-supervised compositional feature representation for video understanding" was invented by Zhipeng Bao (Pittsburgh), Pavel Tokmakov (Santa Monica, Calif.), Adrien David Gaidon (San Jose, Calif.), Allan Jabri (Toronto), Yuxiong Wang (Champaign, Ill.) and Martial Hebert (Pittsburgh).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method of compositional feature representation learning for video understanding is...