US Patent Issued to ADOBE on Feb. 11 for "Visual-semantic representation learning via multi-modal contrastive training" (California, Illinois, Washington Inventors)

ALEXANDRIA, Va., Feb. 12 -- United States Patent no. 12,223,439, issued on Feb. 11, was assigned to ADOBE INC. (San Jose, Calif.).

"Visual-semantic representation learning via multi-modal contrastive training" was invented by Xin Yuan (Chicago), Zhe Lin (Bellevue, Wash.), Jason Wen Yong Kuen (Santa Clara, Calif.), Jianming Zhang (Campbell, Calif.), Yilin Wang (Sunnyvale, Calif.), Ajinkya Kale (San Jose, Calif.) and Baldo Faieta (San Francisco).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for multi-modal representation learning are described. One or more embodiments provide a visual representation learning system trained using machine learning techniques. For example, some embodiments of ...