ALEXANDRIA, Va., April 21 -- United States Patent no. 12,608,647, issued on April 21, was assigned to International Business Machines Corp. (Annonk, N.Y.).
"Multimodal data inference" was invented by Andrea Giovannini (Zurich), Antonio Foncubierta Rodriguez (Zurich), Niharika DSouza (San Jose, Calif.), Tanveer Syeda-Mahmood (Cupertino, Calif.) and Hongzhi Wang (Santa Bruno, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Computer-implemented methods are provided for generating machine learning model for multimodal data inference tasks. Such a method includes, for each sample in a training dataset of multimodal data samples, encoding the sample to produce a compressed vector representation of the sample...