Revisiting Skeleton-based Action Recognition

🤖 Plain-English Summary

Human skeleton, as a compact representation of human action, has received increasing attention in recent years. Once fused with other modalities, it achieves the advanced on all eight multi-modality action recognition benchmarks.

🔑 Key Findings

• Many skeleton-based action recognition methods adopt GCNs to extract features on top of human skeletons.
• Despite the positive results shown in these attempts, GCN-based methods are subject to limitations in robustness, interoperability, and scalability.
• In this work, we propose PoseConv3D, a new approach to skeleton-based action recognition.

🔗 Related Resources