US Patent Issued to Intel on Aug. 18 for "Dynamic temporal normalization for deep learning in video understanding applications" (Chinese Inventors)

ALEXANDRIA, Va., Aug. 18 -- United States Patent no. 12,711,745, issued on Aug. 18, was assigned to Intel Corp. (Santa Clara, Calif.).

"Dynamic temporal normalization for deep learning in video understanding applications" was invented by Dongqi Cai (Beijing), Anbang Yao (Beijing) and Yurong Chen (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques related to application of deep neural networks to video for video recognition and understanding are discussed. A feature map of a deep neural network for a current time stamp of input video is standardized to a standardized feature map and pooled to a feature vector. The feature vector and transform parameters for a prior time stamp are used to genera...