US Patent Issued to InterDigital VC Holdings on July 21 for "Temporal structure-based conditional convolutional neural networks for video compression" (California Inventors)

ALEXANDRIA, Va., July 21 -- United States Patent no. 12,689,762, issued on July 21, was assigned to InterDigital VC Holdings Inc. (Wilmington, Del.).

"Temporal structure-based conditional convolutional neural networks for video compression" was invented by Fabien Racape (San Francisco), Jean Begaint (Menlo Park, Calif.), Simon Feltman (Sunnyvale, Calif.) and Akshay Pushparaja (San Jose, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Video encoding and decoding is implemented with auto encoders using luminance information to derive motion information for chrominance prediction. In one embodiment conditional convolutions are used to encode motion flow information. A current condition, for example, GOP s...