US Patent Issued to Snap on Aug. 4 for "Scaled spatiotemporal transformers for text-to-video synthesis" (California, Washington Inventors)

ALEXANDRIA, Va., Aug. 5 -- United States Patent no. 12,700,160, issued on Aug. 4, was assigned to Snap Inc. (Santa Monica, Calif.).

"Scaled spatiotemporal transformers for text-to-video synthesis" was invented by Tsai-Shien Chen (Merced, Calif.), Yuwei Fang (Redmond, Wash.), Anil Kag (Los Angeles), Willi Menapace (Santa Monica, Calif.), Jian Ren (Hermosa Beach, Calif.), Aliaksandr Siarohin (Los Angeles), Ivan Skorokhodov (Los Angeles) and Sergey Tulyakov (Santa Monica, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A text-to-video framework including a far-reaching interleaved transformer (FIT) block configured to learn a compressed representation of video input using a set of learnable latent tokens....