US Patent Issued to BEIJING JINGDONG SHANGKE INFORMATION TECHNOLOGY on Nov. 3 for "Multi-modal pre-training method and multi-modal pre-training apparatus" (Chinese Inventors)

ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,784,415, issued on Nov. 3, was assigned to BEIJING JINGDONG SHANGKE INFORMATION TECHNOLOGY Co. LTD. (Beijing).

"Multi-modal pre-training method and multi-modal pre-training apparatus" was invented by Yehao Li (Beijing), Yingwei Pan (Beijing), Ting Yao (Beijing) and Tao Mei (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure provides a multi-modal pre-training method and apparatus. The method includes: sampling a video in a video-text pair to obtain a first video frame sequence; performing word segmentation processing on a text in the video-text pair to obtain a first word segmentation sequence; masking on the first video frame ...