Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition

By Yuxin Chen, Ziqi Zhang, Chunfen Yuan, Bing Li, Ying Deng, Weiming Hu. IEEE International Conference on Computer Vision, 2021

930 citations recorded by the source corpus.

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.1

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b5b717bd65678b9b980ae3f2aaea0396e87ab0e2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jun Liu
2. Hossein Rahmani
3. Qiuhong Ke
4. Zehua Sun
5. Dahua Lin
6. Kai Chen
7. Bo Dai
8. Hyung-gun Chi

In Biomedical Engineering

1. Jun Liu
2. Qiuhong Ke
3. Hossein Rahmani
4. Zehua Sun
5. Yue Zhao
6. Bo Dai
7. Dian Shao
8. Dahua Lin

In Computer Vision and Pattern Recognition

1. Jun Liu
2. Hossein Rahmani
3. Qiuhong Ke
4. Luc Van Gool
5. Dahua Lin
6. Bo Dai
7. G. Wang
8. Dacheng Tao

Citations in the corpus

• InfoGCN: Representation Learning for Human Skeleton-based Action Recognition (2022, methodology): “…[44] 88.5 95.1 SGN [60] 89.0 94.5 DGNN [43] 89.9 96.1 ST-TR-agcn [39] 90.3 96.3 Shift-GCN [9] 90.7 96.5 DC-GCN+ADG [8] 90.8 96.6 PA-ResGCN-B19 [47] 90.9 96.0 DDGCN [22] 91.1 97.1 Dynamic GCN [58] 91.5 96.0 MS-G3D [33] 91.5 96.2 MST-GCN [7] 91.5 96.6 CTR-GCN [6] 92.4 96.8 Ours 93.0 97.1 Acc (”
• Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “[241] proposed a Channel-wise Topology Refinement Graph Convolution (CTR-GC) for dynamic topology and multi-channel feature modeling.”
• Revisiting Skeleton-based Action Recognition (2021, background): “Graph convolutional network is widely adopted in skeleton-based action recognition [3,7,19,55,56,71].”