no code implementations • 8 Sep 2021 • Sangpil Kim, Jihyun Bae, Hyunggun Chi, Sunghee Hong, Byoung Soo Koh, Karthik Ramani
We introduce a multi-stage framework that uses mean curvature on a hand surface and focuses on learning interaction between hand and object by analyzing hand grasp type for hand action recognition in egocentric videos.