Research map / Graph learning / Knowledge and temporal graphs
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
Check 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 |
|---|---|---|---|
| Replace fixed skeleton connectivity with learnable global and sample-dependent graph structures while retaining the physical graph | AGCN · NTU-RGBD X-View | accuracy: 92.7 -> 93.7 | Helped |
| Add the physical-structure graph A (ablation) | AGCN · NTU-RGBD X-View | accuracy: 93.4 -> 93.7 | Helped |
| Add the learned global graph B (ablation) | AGCN · NTU-RGBD X-View | accuracy: 93.3 -> 93.7 | Helped |
| Add the sample-dependent graph C (ablation) | AGCN · NTU-RGBD X-View | accuracy: 93.4 -> 93.7 | Helped |
| Remove the connection-strength mask M (ablation) | ST-GCN · NTU-RGBD X-View | accuracy: 92.7 -> 91.1 | Hurt |
| Fuse joint-coordinate and bone-vector streams (ablation) | 2s-AGCN · NTU-RGBD X-View | accuracy: 93.7 -> 95.1 | Helped |
| Fuse joint-coordinate and bone-vector streams (ablation) | 2s-AGCN · Kinetics-Skeleton validation | top-1 accuracy: 35.1 -> 36.1 | Helped |
| Fuse joint-coordinate and bone-vector streams (ablation) | 2s-AGCN · Kinetics-Skeleton validation | top-5 accuracy: 57.1 -> 58.7 | Helped |
| Use the revised learning-rate scheduler and specially designed data preprocessing | ST-GCN · NTU-RGBD X-View | accuracy: 88.3 -> 92.7 | Helped |
Closest papers by meaning
- Learning Graph Convolutional Network for Skeleton-Based Human Action Recognition by Neural Searching (AAAI 2020 · similarity 0.94)
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition (AAAI 2024 · similarity 0.94)
- Skeleton-Based Action Recognition With Shift Graph Convolutional Network (CVPR 2020 · similarity 0.94)
- BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition (CVPR 2024 · similarity 0.92)
- 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 0.90)
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.