Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
About
Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint dependencies and short-term trajectory but fails to directly model the distant joints relations and long-range temporal information that are vital to distinguishing various actions. To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal dimensions. Concretely, the MS-GC and MT-GC modules decompose the corresponding local graph convolution into a set of sub-graph convolution, forming a hierarchical residual architecture. Without introducing additional parameters, the features will be processed with a series of sub-graph convolutions, and each node could complete multiple spatial and temporal aggregations with its neighborhoods. The final equivalent receptive field is accordingly enlarged, which is capable of capturing both short- and long-range dependencies in spatial and temporal domains. By coupling these two modules as a basic block, we further propose a multi-scale spatial temporal graph convolutional network (MST-GCN), which stacks multiple blocks to learn effective motion representations for action recognition. The proposed MST-GCN achieves remarkable performance on three challenging benchmark datasets, NTU RGB+D, NTU-120 RGB+D and Kinetics-Skeleton, for skeleton-based action recognition.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Action Recognition | NTU RGB+D 120 (X-set) | Accuracy88.8 | 661 | |
| Action Recognition | NTU RGB+D (Cross-View) | Accuracy96.6 | 609 | |
| Action Recognition | NTU RGB+D 60 (Cross-View) | Accuracy96.6 | 575 | |
| Action Recognition | NTU RGB+D (Cross-subject) | Accuracy91.5 | 474 | |
| Action Recognition | NTU RGB+D 60 (X-sub) | Accuracy91.5 | 467 | |
| Action Recognition | NTU RGB+D X-sub 120 | Accuracy87.5 | 377 | |
| Action Recognition | NTU RGB-D Cross-Subject 60 | Accuracy91.5 | 305 | |
| Skeleton-based Action Recognition | NTU 60 (X-sub) | Accuracy91.5 | 220 | |
| Skeleton-based Action Recognition | NTU RGB+D (Cross-View) | Accuracy96.6 | 213 | |
| Skeleton-based Action Recognition | NTU RGB+D 120 (X-set) | Top-1 Accuracy88.8 | 184 |