ALEXANDRIA, Va., June 25 -- United States Patent no. 12,340,571, issued on June 24, was assigned to Adobe Inc. (San Jose, Calif.).
"Using intrinsic multimodal features of image for domain generalized" was invented by Puneet Mangla (Ballabgarh, India), Milan Aggarwal (Delhi, India) and Balaji Krishnamurthy (Uttar Pradesh, India).
According to the abstract* released by the U.S. Patent & Trademark Office: "Various embodiments classify one or more portions of an image based on deriving an "intrinsic" modality. Such intrinsic modality acts as a substitute to a "text" modality in a multi-modal network. A text modality in image processing is typically a natural language text that describes one or more portions of an image. However, explicit natu...