Research map / Graph learning / Knowledge and temporal graphs
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use spatial-temporal graph convolution instead of temporal convolution over concatenated joint coordinates (ablation) | ST-GCN on Kinetics · Kinetics validation | top-1 accuracy: 20.3% -> 29.9% | Helped |
| Use shared graph-convolution weights rather than unshared local-convolution weights (ablation) | ST-GCN on Kinetics · Kinetics validation | top-1 accuracy: 22.0% -> 29.9% | Helped |
| Use multiple neighbor subsets instead of uni-labeling (ablation) | ST-GCN on Kinetics · Kinetics validation | top-1 accuracy: 19.3% -> 29.9% | Helped |
| Use distance partitioning instead of uni-labeling (ablation) | ST-GCN on Kinetics · Kinetics validation | top-1 accuracy: 19.3% -> 29.1% | Helped |
| Use spatial-configuration partitioning instead of distance partitioning (ablation) | ST-GCN on Kinetics · Kinetics validation | top-1 accuracy: 29.1% -> 29.9% | Helped |
| Add learnable edge-importance weighting (ablation) | ST-GCN with spatial-configuration partitioning · Kinetics validation | top-1 accuracy: 29.9% -> 30.7% | Helped |
| Add ST-GCN to the RGB model | RGB TSN ensemble on Kinetics · Kinetics | accuracy: 70.3 -> 71.2 | Helped |
| Combine RGB, optical flow, and ST-GCN | Kinetics multimodal ensemble · Kinetics | accuracy: 71.7% | Helped |
Closest papers by meaning
- Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (AAAI 2021 · similarity 0.95)
- Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition (AAAI 2018 · similarity 0.95)
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition (AAAI 2024 · similarity 0.94)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.92)
- Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized? (CVPR 2025 · similarity 0.92)
- BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition (CVPR 2024 · similarity 0.91)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.