US Patent Issued to NVIDIA on Aug. 11 for "Global context vision transformer" (California, Massachusetts Inventors)

ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,705,856, issued on Aug. 11, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Global context vision transformer" was invented by Ali Hatamizadeh (Los Angeles), Pavlo Molchanov (Mountain View, Calif.), Hongxu Yin (San Jose, Calif.) and Jan Kautz (Lexington, Mass.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Vision transformers are deep learning models that employ a self-attention mechanism to obtain feature representations for an input image. To date, the configuration of vision transformers has limited the self-attention computation to a local window of the input image, such that short-range dependencies are modeled in the output. The present discl...