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

🤖 Plain-English Summary

Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. Combining CTR-GC with temporal modeling modules, we develop a powerful graph convolutional network named CTR-GCN which notably outperforms advanced methods on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.

🔑 Key Findings

• 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.

🔗 Related Resources