US Patent Issued to SNAP on Sept. 8 for "Automated captioning of augmented reality effects in videos" (New Jersey, New York, California Inventors)

ALEXANDRIA, Va., Sept. 8 -- United States Patent no. 12,730,971, issued on Sept. 8, was assigned to SNAP INC. (Santa Monica, Calif.).

"Automated captioning of augmented reality effects in videos" was invented by Kwot Sin Lee (Weehawken, N.J.), Varnith Uttam Chordia (Jersey City, N.J.), Jacob Assa (New York) and Maryna Diakonova (Playa Vista, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Described herein are techniques for generating captions for augmented reality (AR) effects in videos using an adapted multimodal large language model (MLLM). The technique involves sampling frames from base and AR-applied videos, combining them into concatenated frames, and processing them with a hybrid vision encoder...