ALEXANDRIA, Va., Dec. 9 -- United States Patent no. 12,494,053, issued on Dec. 9, was assigned to GOOGLE LLC (Mountain View, Calif.).
"Multi-axis vision transformer" was invented by Yinxiao Li (Sunnyvale, Calif.), Feng Yang (Sunnyvale, Calif.), Peyman Milanfar (Menlo Park, Calif.), Han Zhang (Sunnyvale, Calif.), Zhengzhong Tu (Austin, Texas) and Hossein Talebi (San Jose, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Provided is an efficient and scalable attention model that can be referred to as multi-axis attention. Example implementations can include two aspects: blocked local and dilated global attention. These design choices allow global-local spatial interactions on arbitrary input resolutions w...