Research map / Graph learning / Knowledge and temporal graphs
Spatio-Temporal Graph Routing 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 Deep STGC_K instead of the strongest listed baseline | skeleton action recognition · Florence 3D | accuracy: 95.35% -> 99.07% | Helped |
| use Deep STGC_K instead of the strongest listed baseline | skeleton action recognition · HDM05 Protocol 1 | accuracy: 70.4% -> 78.7% | Helped |
| use Deep STGC_K instead of the strongest listed baseline | skeleton action recognition · HDM05 Protocol 2 | accuracy: 75.78%$\pm$2.26 -> 85.29%$\pm$1.33 | Helped |
| use Deep STGC_K instead of the strongest listed baseline | skeleton action recognition · LSC Cross Subject | precision: 76.3% -> 85.4% | Helped |
| use Deep STGC_K instead of the strongest listed baseline | skeleton action recognition · NTU RGB+D Cross Subject | accuracy: 79.57% -> 74.85% | Hurt |
| add one-hop graph neighborhood filtering (ablation) | STGC · Florence 3D | accuracy: 98.14% -> 98.60% | Helped |
| model interactions among signals rather than assuming signal independence (ablation) | STGC_K · HDM05 Protocol 1 | accuracy: 77.08% -> 77.99% | Helped |
| stack STGC_K into a two-layer deep architecture (ablation) | STGC_K (dep.) · HDM05 Protocol 1 | accuracy: 77.99% -> 78.68% | Helped |
| stack STGC_K into a two-layer deep architecture (ablation) | STGC_K (dep.) · NTU RGB+D Cross View | accuracy: 81.84% -> 86.28% | Helped |
| stack STGC_K into a two-layer deep architecture (ablation) | STGC_K (dep.) · NTU RGB+D Cross Subject | accuracy: 72.09% -> 74.85% | Helped |
| stack independent-signal STGC_K into a two-layer architecture (ablation) | STGC_K (indep.) · HDM05 Protocol 2 | accuracy: 82.49%$\pm$1.49 -> 86.17%$\pm$1.25 | Helped |
| increase temporal kernel scale K1 and spatial kernel scale K2 (ablation) | STGC_K · HDM05 Protocol 1 | accuracy | Mixed |
Closest papers by meaning
- Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (AAAI 2021 · similarity 0.93)
- Spatio-Temporal Fusion for Human Action Recognition via Joint Trajectory Graph (AAAI 2024 · similarity 0.93)
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition (AAAI 2024 · similarity 0.92)
- BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition (CVPR 2024 · similarity 0.91)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.90)
- Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized? (CVPR 2025 · similarity 0.89)
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.