US Patent Issued to Adobe on June 24 for "Self-supervised audio-visual learning for correlating music and video" (California, New York Inventors)

ALEXANDRIA, Va., June 25 -- United States Patent no. 12,340,563, issued on June 24, was assigned to Adobe Inc. (San Jose, Calif.).

"Self-supervised audio-visual learning for correlating music and video" was invented by Justin Salamon (San Francisco), Bryan Russell (San Francisco) and Didac Suris Coll-Vinent (New York).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments are disclosed for correlating video sequences and audio sequences by a media recommendation system using a trained encoder network. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a training input including a media sequence, including a video sequence paired with an audio sequence, segmenti...