US Patent Issued to Beijing Baidu Netcom Science Technology Co. Ltd. China on July 1 for "Pre-training method, image and text retrieval method for a vision and scene text aggregation model, electronic device, and storage medium" (Chinese Inventors)

ALEXANDRIA, Va., July 3 -- United States Patent no. 12,347,158, issued on July 1, was assigned to Beijing Baidu Netcom Science Technology Co. Ltd. China (Beijing).

"Pre-training method, image and text retrieval method for a vision and scene text aggregation model, electronic device, and storage medium" was invented by Yipeng Sun (Beijing), Mengjun Cheng (Beijing), Longchao Wang (Beijing), Xiongwei Zhu (Beijing), Kun Yao (Beijing), Junyu Han (Beijing), Jingtuo Liu (Beijing), Errui Ding (Beijing), Jingdong Wang (Beijing) and Haifeng Wang (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "A pre-training method for a Vision and Scene Text Aggregation model includes: acquiring a sample image-text pair; extra...