Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos

no code implementations • 14 Feb 2024 • Yang Qian, Yinan Sun, Ali Kargarandehkordi, Parnian Azizian, Onur Cezmi Mutlu, Saimourya Surabhi, Pingyi Chen, Zain Jabbar, Dennis Paul Wall, Peter Washington

These results highlight the potential of using unstructured and unlabeled videos as a valuable source of diverse and dynamic content for training foundation models.

Action Recognition Self-Supervised Learning +1