Recognize Actions by Disentangling Components of Dynamics
CVPR, pp. 6566-6575, 2018.
Despite the remarkable progress in action recognition over the past several years, existing methods remain limited in efficiency and effectiveness. The methods treating appearance and motion as separate streams are usually subject to the cost of optical flow computation, while those relying on 3D convolution on the original video frames o...More
PPT (Upload PPT)