Papers › Skeleton-Based Action Recognition With Shift Graph Convolutional Network
Skeleton-Based Action Recognition With Shift Graph Convolutional Network
Ke Cheng, Yifan Zhang, Xiangyu He, Weihan Chen, Jian Cheng, Hanqing Lu
Action recognition with skeleton data is attracting more attention in computer vision. Recently, graph convolutional networks (GCNs), which model the human body skeletons as spatiotemporal graphs, have obtained remarkable performance. However, the computational complexity of GCN-based methods are pretty heavy, typically over 15 GFLOPs for one action sample. Recent works even reach about 100 GFLOPs. Another shortcoming is that the receptive fields of both spatial graph and temporal graph are inflexible. Although some works enhance the expressiveness of spatial graph by introducing incremental adaptive modules, their performance is still limited by regular GCN structures. In this paper, we propose a novel shift graph convolutional network (Shift-GCN) to overcome both shortcomings. Instead of using heavy regular graph convolutions, our Shift-GCN is composed of novel shift graph operations and lightweight point-wise convolutions, where the shift graph operations provide flexible receptive fields for both spatial graph and temporal graph. On three datasets for skeleton-based action recognition, the proposed Shift-GCN notably exceeds the state-of-the-art methods with more than 10 times less computational complexity.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Skeleton Based Action Recognition | NTU RGB+D | 4s Shift-GCN | Accuracy (CS) | 90.7 | #46 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | 4s Shift-GCN | Accuracy (CV) | 96.5 | #46 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D | 4s Shift-GCN | Ensembled Modalities | 4 | #46 of 135 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | 4s Shift-GCN | Accuracy (Cross-Setup) | 87.6% | #42 of 83 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | 4s Shift-GCN | Accuracy (Cross-Subject) | 85.9% | #42 of 83 | Archive leaderboard | report |
| Skeleton Based Action Recognition | NTU RGB+D 120 | 4s Shift-GCN | Ensembled Modalities | 4 | #42 of 83 | Archive leaderboard | report |
| Skeleton Based Action Recognition | UAV-Human | Shift-GCN | CSv1(%) | 37.98 | #5 of 9 | Archive leaderboard | report |
| Skeleton Based Action Recognition | UAV-Human | Shift-GCN | CSv2(%) | 67.04 | #5 of 9 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections