US Patent Issued to Adobe on Sept. 23 for "Per-clip video object segmentation using machine learning" (South Korean, American Inventors)

ALEXANDRIA, Va., Sept. 23 -- United States Patent no. 12,423,979, issued on Sept. 23, was assigned to Adobe Inc. (San Jose, Calif.).

"Per-clip video object segmentation using machine learning" was invented by Joon-Young Lee (San Jose, Calif.), Seoung Wug Oh (San Jose, Calif.), Sanghyun Woo (Daejeon, South Korea) and Kwanyong Park (Daejeon, South Korea).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments are disclosed for performing per-clip object segmentation of objects in a video sequence using machine learning. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a query video sequence and memory data, the memory data including a memory video frame from the...