US Patent Issued to DeepMind Technologies on April 15 for "Generative adversarial networks with temporal and spatial discriminators for efficient video generation" (British Inventors)

ALEXANDRIA, Va., June 5 -- United States Patent no. 12,277,672, issued on April 15, was assigned to DeepMind Technologies Ltd. (London).

"Generative adversarial networks with temporal and spatial discriminators for efficient video generation" was invented by Aidan Clark (London), Jeffrey Donahue (London) and Karen Simonyan (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure proposes the use of a dual discriminator network that comprises a temporal discriminator network for discriminating based on temporal features of a series of images and a spatial discriminator network for discriminating based on spatial features of individual images. The training methods described herein provide ...