US Patent Issued to The Toronto-Dominion Bank on Oct. 14 for "Text-conditioned video representation" (Canadian Inventors)

ALEXANDRIA, Va., Oct. 21 -- United States Patent no. 12,444,194, issued on Oct. 14, was assigned to The Toronto-Dominion Bank (Toronto).

"Text-conditioned video representation" was invented by Satya Krishna Gorti (Toronto), Junwei Ma (Toronto), Guangwei Yu (Toronto), Maksims Volkovs (Toronto), Keyvan Golestan Irani (Toronto) and Noel Vouitsis (Toronto).

According to the abstract* released by the U.S. Patent & Trademark Office: "A text-video recommendation model determines relevance of a text to a video in a text-video pair (e.g., as a relevance score) with a text embedding and a text-conditioned video embedding. The text-conditioned video embedding is a representation of the video used for evaluating the relevance of the video to the text...