US Patent Issued to Adobe on Sept. 15 for "Text-conditioned visual attention for multimodal machine learning models" (Indian Inventors)

ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,738,041, issued on Sept. 15, was assigned to Adobe Inc. (San Jose, Calif.).

"Text-conditioned visual attention for multimodal machine learning models" was invented by Prateksha Udhayanan (Bangalore, India), Srikrishna Karanam (Bangalore, India) and Balaji Vasan Srinivasa (Bangalore, India).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure relates to systems, non-transitory computer-readable media, and methods for conditioning images on modification texts to generate multi-modal gradient attention maps. In particular, in some embodiments, the disclosed systems generate, utilizing a vision-language neural network of an image-text compa...