ALEXANDRIA, Va., July 14 -- United States Patent no. 12,682,606, issued on July 14, was assigned to LandingAI Inc. (Palo Alto, Calif.).

"Output accuracy refinement mechanism for visual prompting" was invented by Abdelhamid Bouzid (Louisville, Ky.), Mark William Sabini (River Edge, N.J.), Bastian Diaz Renjifo (Santiago, Chile), Whitney Wentworth Blodgett (San Francisco), Kai Yang (Fremont, Calif.), Andrew Yan-Tak Ng (Camas, Wash.) and Daniel Bibireata (Bellevue, Wash.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A device inputs a raw image into a machine learning model, and receives a predicted image comprising a plurality of masks as output from the machine learning model, each mask of the plurality of mas...