US Patent Issued to Carnegie Mellon University on June 10 for "Methods for improving datasets for skeleton-based action detection" (Pennsylvania Inventors)

ALEXANDRIA, Va., June 18 -- United States Patent no. 12,327,338, issued on June 10, was assigned to Carnegie Mellon University (Pittsburgh).

"Methods for improving datasets for skeleton-based action detection" was invented by Marios Savvides (Pittsburgh), Yu Kai Huang (Pittsburgh) and Eddie Yu (Pittsburgh).

According to the abstract* released by the U.S. Patent & Trademark Office: "Disclosed here are various techniques for improving the testing and training of datasets comprising sequences of skeletal representations performing various actions. The dataset can be denoised by applying various techniques to determine noisy frames within each sequence and eliminating the sequences from the dataset when the number of noisy frames in the seque...