Recognize Actions by Disentangling Components of Dynamics

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 6566 - 6575
• Main Authors: Zhao, Yue, Xiong, Yuanjun, Lin, Dahua
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Computational modeling; Convolution; Feature extraction; Integrated optics; Optical computing; Optical imaging; Three-dimensional displays
• ISSN: 1063-6919
• DOI: 10.1109/CVPR.2018.00687

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 co...