US Patent Issued to Google on Feb. 24 for "Cross-modal contrastive learning for text-to-image generation based on machine learning models" (American, Singaporean Inventors)

ALEXANDRIA, Va., Feb. 24 -- United States Patent no. 12,561,852, issued on Feb. 24, was assigned to Google LLC (Mountain View, Calif.).

"Cross-modal contrastive learning for text-to-image generation based on machine learning models" was invented by Han Zhang (Sunnyvale, Calif.), Jing Yu Koh (Singapore), Jason Michael Baldridge (Austin, Texas), Yinfei Yang (Sunnyvale, Calif.) and Honglak Lee (Ann Arbor, Mich.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method includes receiving, by a computing device, a particular textual description of a scene. The method also includes applying a neural network for text-to-image generation to generate an output image rendition of the scene, the neur...