Journal
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
Volume -, Issue -, Pages 2959-2968Publisher
IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.00298
Keywords
-
Funding
- General Research Funds of Hong Kong [14203518]
- RIE2020 Industry Alignment Fund-Industry Collaboration Projects (IAF-ICP) Funding Initiative
- Shanghai Committee of Science and Technology [20DZ1100800]
Ask authors/readers for more resources
This paper proposes a new approach called PoseConv3D for skeleton-based action recognition. Compared to GCN-based methods, PoseConv3D is more effective in learning spatiotemporal features, more robust against pose estimation noises, and generalizes better in cross-dataset settings. It can also handle multiple-person scenarios without additional computation costs and can be easily integrated with other modalities.
Human skeleton, as a compact representation of human action, has received increasing attention in recent years. 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. PoseConv3D relies on a 3D heatmap volume instead of a graph sequence as the base representation of human skeletons. Compared to GCN-based methods, PoseConv3D is more effective in learning spatiotemporal features, more robust against pose estimation noises, and generalizes better in cross-dataset settings. Also, PoseConv3D can handle multiple-person scenarios without additional computation costs. The hierarchical features can be easily integrated with other modalities at early fusion stages, providing a great design space to boost the performance. PoseConv3D achieves the state-of-the-art on five of six standard skeleton-based action recognition benchmarks. Once fused with other modalities, it achieves the state-of-the-art on all eight multi-modality action recognition benchmarks. Code has been made available at: https://github.com/kennymckormick/pyskl.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available