Paper Info
Title
Multi-stream mixed graph convolutional networks for skeleton-based action recognition
Abstract
The skeleton-based action recognition task has recently drawn much attention in computer vision, and graph convolutional networks (GCNs) have shown great advantages in this task. However, in shallow layers of GCNs, the sharing of convolution kernels in regular graph convolution (RGC) may result in the underutilization of some convolution kernels due to the particularity of the skeleton data. To capture richer locally discriminative action features, we propose the exclusive kernel graph convolution (EKGC) for the shallow layers of GCNs, which assigns the vertexes exclusive convolution kernels for graph convolution. At the same time, following the mixed graph convolution strategy, RGC is retained in the deep layers of the network, and the mixed graph convolutional network (MGCN) is proposed to utilize EKGC and RGC reasonably in all layers of the network. In addition, as a new form of skeleton information in GCN-based methods, angle information is explored in our work. Compared with joint data and bone data, angle data have better invariance against rotation and scaling, and they expand the relationships between skeletons and enrich the data representation of action. Finally, our final model, the multi-stream MGCN, is validated on two challenging datasets, achieving the state-of-the-art performance on the NTU-RGBD dataset and making competitive performance on a kinetics skeleton dataset. (C) 2021 SPIE and IS&T
Year
DOI
Venue
2021
10.1117/1.JEI.30.6.063012
JOURNAL OF ELECTRONIC IMAGING
Keywords
DocType
Volume
skeleton-based action recognition, exclusive kernel graph convolution, mixed graph convolutional network, angle information, multi-modality data
Journal
30
Issue
ISSN
Citations 
6
1017-9909
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
Boyuan Zhuang100.34
Jun Kong215814.14
Min Jiang33913.65
Tianshan Liu494.27