US Patent Issued to Intel on Nov. 3 for "Bidirectional compact deep fusion networks for multimodality visual analysis applications" (Chinese Inventors)

ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,784,396, issued on Nov. 3, was assigned to Intel Corp. (Santa Clara, Calif.).

"Bidirectional compact deep fusion networks for multimodality visual analysis applications" was invented by Dongqi Cai (Beijing), Anbang Yao (Beijing), Yikai Wang (Beijing), Ming Lu (Beijing) and Yurong Chen (Beijing).

According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques related to bidirectional compact deep fusion networks for multimodal image inputs are discussed. Such techniques include applying a shared convolutional layer and independent batch normalization layers to input volumes for each modality and fusing features from the resultant output volumes in both directions...