Open AccessVideo Human Action Recognition with Channel Attention on ST-GCN
Author(s) -
Deyuan Zhang,
Haoguang Wang,
Chao Weng,
Xun Shi
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2010/1/012131
Subject(s) - computer science , rgb color model , artificial intelligence , channel (broadcasting) , human skeleton , feature (linguistics) , action recognition , pattern recognition (psychology) , graph , skeleton (computer programming) , convolutional neural network , process (computing) , computer vision , theoretical computer science , computer network , philosophy , linguistics , programming language , class (philosophy) , operating system
Action recognition based on human skeleton information is a hot research topic in the field of computer vision, and ST-GCN graph convolutional network is widely used to extract spatial and temporal features of human skeleton to represent the human skeleton structure. However, in the process of extracting features, the weights on each channel of the feature are the same, so it is difficult to effectively discriminate the useful features from the useless ones. In this paper, we propose Channel Attention module, which learns the importance of each feature channel to perform human action recognition more effectively. Experimental results on Kinetics and NTU-RGB+D datasets show that Channel Attention module can achieve better accuracy.