Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition
arXiv:1802.09834
Abstract
Variations of human body skeletons may be considered as dynamic graphs, which are generic data representation for numerous real-world applications. In this paper, we propose a spatio-temporal graph convolution (STGC) approach for assembling the successes of local convolutional filtering and sequence learning ability of autoregressive moving average. To encode dynamic graphs, the constructed multi-scale local graph convolution filters, consisting of matrices of local receptive fields and signal mappings, are recursively performed on structured graph data of temporal and spatial domain. The proposed model is generic and principled as it can be generalized into other dynamic models. We theoretically prove the stability of STGC and provide an upper-bound of the signal transformation to be learnt. Further, the proposed recursive model can be stacked into a multi-layer architecture. To evaluate our model, we conduct extensive experiments on four benchmark skeleton-based action datasets, including the large-scale challenging NTU RGB+D. The experimental results demonstrate the effectiveness of our proposed model and the improvement over the state-of-the-art.
arXiv commentAccepted by AAAI 2018
References in corpus (9)
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Biological network comparison using graphlet degree distribution
- Learning Convolutional Neural Networks for Graphs
- Unstructured Human Activity Detection from RGBD Images
- Gated Graph Sequence Neural Networks
- NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
- A Riemannian Network for SPD Matrix Learning
- Action-Attending Graphic Neural Network
- Deep Learning on Lie Groups for Skeleton-based Action Recognition