US Patent Issued to ADOBE on April 15 for "Multimodal unsupervised video temporal segmentation for summarization" (California, Pennsylvania Inventors)

ALEXANDRIA, Va., June 5 -- United States Patent no. 12,277,767, issued on April 15, was assigned to ADOBE INC. (San Jose, Calif.).

"Multimodal unsupervised video temporal segmentation for summarization" was invented by Hailin Jin (San Jose, Calif.), Jielin Qiu (Pittsburgh), Zhaowen Wang (San Jose, Calif.), Trung Huu Bui (San Jose, Calif.) and Franck Dernoncourt (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for video segmentation and summarization are described. Embodiments of the present disclosure receive a video and a transcript of the video; generate visual features representing frames of the video using an image encoder; generate language features representing the t...