Research map / Graph learning / Knowledge and temporal graphs
Context Aware Graph Convolution 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 |
|---|---|---|---|
| Add context-aware graph convolution to ST-GCN | ST-GCN · Kinetics | top-1 accuracy: 30.7% -> 34.1% | Helped |
| Add context-aware graph convolution | ST-GCN · NTU-RGB+D cross-subject | top-1 accuracy: 81.5% -> 83.5% | Helped |
| Add context-aware graph convolution | ST-GCN · NTU-RGB+D cross-view | top-1 accuracy: 88.3% -> 91.4% | Helped |
| Add context-aware graph convolution | GECNN · Kinetics | top-1 accuracy: 31.4% -> 32.6% | Helped |
| Add context-aware graph convolution | BPLHM · NTU-RGB+D cross-subject | top-1 accuracy: 85.4% -> 86.5% | Helped |
| Use context-aware graph convolution with trainable relevance and concatenation (ablation) | ST-GCN · Kinetics | top-1 accuracy: 30.7% -> 33.3% | Helped |
| Use concatenation rather than addition to integrate context (ablation) | CA-GCN with inner-product relevance · Kinetics | top-1 accuracy: 32.0% -> 32.9% | Helped |
| Use concatenation rather than addition to integrate context (ablation) | CA-GCN with bi-linear relevance · Kinetics | top-1 accuracy: 32.2% -> 33.0% | Helped |
| Use concatenation rather than addition to integrate context (ablation) | CA-GCN with trainable relevance · Kinetics | top-1 accuracy: 33.1% -> 33.3% | Helped |
| Replace inner-product relevance with bi-linear relevance, keeping addition integration (ablation) | CA-GCN · Kinetics | top-1 accuracy: 32.0% -> 32.2% | Helped |
| Replace bi-linear relevance with trainable relevance, keeping concatenation integration (ablation) | CA-GCN · Kinetics | top-1 accuracy: 33.0% -> 33.3% | Helped |
| Reduce CA-GCN depth from 9 layers to 6 (ablation) | CA-GCN · Kinetics | top-1 accuracy: 33.3% -> 31.4% | Hurt |
Closest papers by meaning
- Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (AAAI 2021 · similarity 0.94)
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition (AAAI 2024 · similarity 0.93)
- 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 0.91)
- Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized? (CVPR 2025 · similarity 0.91)
- Spatio-Temporal Fusion for Human Action Recognition via Joint Trajectory Graph (AAAI 2024 · 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.