Title | ||
---|---|---|
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition. |
Abstract | ||
---|---|---|
Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. In GCNs, graph topology dominates feature aggregation and therefore is the key to extracting representative features. In this work, we propose a novel Channel-wise Topology Refinement Graph Convolution (CTR-GC) to dynamically learn different topologies and effectively aggregate joint features in different channels for skeleton-based action recognition. The proposed CTR-GC models channel-wise topologies through learning a shared topology as a generic prior for all channels and refining it with channel-specific correlations for each channel. Our refinement method introduces few extra parameters and significantly reduces the difficulty of modeling channel-wise topologies. Furthermore, via reformulating graph convolutions into a unified form, we find that CTR-GC relaxes strict constraints of graph convolutions, leading to stronger representation capability. Combining CTR-GC with temporal modeling modules, we develop a powerful graph convolutional network named CTR-GCN which notably outperforms state-of-the-art methods on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICCV48922.2021.01311 | ICCV |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuxin Chen | 1 | 3 | 0.71 |
Ziqi Zhang | 2 | 312 | 28.90 |
Chunfeng Yuan | 3 | 0 | 1.01 |
Bing Li | 4 | 217 | 60.28 |
Ying Deng | 5 | 0 | 0.68 |
Weiming Hu | 6 | 5300 | 261.38 |