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

26 Jul 2021  ·  Yuxin Chen, Ziqi Zhang, Chunfeng Yuan, Bing Li, Ying Deng, Weiming Hu ·

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. read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Skeleton Based Action Recognition NTU RGB+D CTR-GCN Accuracy (CV) 96.8 # 2
Accuracy (CS) 92.4 # 2
Skeleton Based Action Recognition NTU RGB+D 120 CTR-GCN Accuracy (Cross-Subject) 88.9 # 1
Accuracy (Cross-Setup) 90.6 # 1
Skeleton Based Action Recognition N-UCLA CTR-GCN Accuracy 96.5 # 1