ALEXANDRIA, Va., Nov. 18 -- United States Patent no. 12,475,379, issued on Nov. 18, was assigned to Anumana Inc. (Cambridge, Mass.).
"Systems and methods for training multimodal self-supervised models" was invented by Sairam Bade (Thelangana, India), Rakesh Barve (Bengaluru, India), Ashim Prasad (Bangalore, India) and Yash Mishra (Bangalore, India).
According to the abstract* released by the U.S. Patent & Trademark Office: "A system for training multimodal self-supervised models, the system including a computing device configured to receive a multimodal dataset encode each data entry of a plurality of data entries into a single data format to create an encoded multimodal dataset including one or more encoded modalities, identify one or mo...