US Patent Issued to GDM Holding on March 24 for "Unsupervised learning of object representations from video sequences using attention over space and time" (British, American Inventors)

ALEXANDRIA, Va., March 24 -- United States Patent no. 12,586,353, issued on March 24, was assigned to GDM Holding LLC (Mountain View, Calif.).

"Unsupervised learning of object representations from video sequences using attention over space and time" was invented by Rishabh Kabra (London), Daniel Zoran (London), Goker Erdogan (London), Antonia Phoebe Nina Creswell (London), Loic Matthey-de-l'Endroit (London), Matthew Botvinick (Philadelphia), Alexander Lerchner (London) and Christopher Paul Burgess (Purley, Great Britain).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented video generation neural network system, configured to determine a value for each of a set of object latent variables by s...