Research map / Graph learning / Knowledge and temporal graphs
Learning Graph Convolutional Network for Skeleton-Based Human Action Recognition by Neural Searching
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 temporal representation correlations instead of the structure-correlation baseline (ablation) | GCN action recognition · NTU RGB+D Cross-view (Bone) | accuracy: 93.2 -> 93.7 | Helped |
| Use spatial-temporal representation correlations rather than temporal correlations alone (ablation) | GCN action recognition · NTU RGB+D Cross-view (Joint) | accuracy: 93.8 -> 94.0 | Helped |
| Add 4-order Chebyshev approximation to temporal correlations (ablation) | GCN action recognition · NTU RGB+D Cross-view (Bone) | accuracy: 93.7 -> 93.9 | Helped |
| Add 4-order Chebyshev approximation to spatial-temporal correlations (ablation) | GCN action recognition · NTU RGB+D Cross-view (Joint) | accuracy: 94.0 -> 94.2 | Helped |
| Combine all dynamic graph modules and Chebyshev components in the same block (ablation) | GCN action recognition · NTU RGB+D Cross-view (Joint) | accuracy: 94.2 -> 93.9 | Hurt |
| Search layer-specific graph modules rather than share one module configuration throughout the network (ablation) | GCN action recognition · NTU RGB+D Cross-view (Joint) | accuracy: 93.9 -> 94.6 | Helped |
| Use the searched architecture with joint-and-bone score fusion | Skeleton action recognition · NTU RGB+D Cross-subject | Top-1 accuracy: 88.5 -> 89.4 | Helped |
| Use the searched architecture with joint-and-bone score fusion | Skeleton action recognition · Kinetics-Skeleton | Top-5 accuracy: 58.7 -> 60.1 | Helped |
Closest papers by meaning
- Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition (CVPR 2019 · similarity 0.94)
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition (AAAI 2018 · similarity 0.94)
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition (AAAI 2024 · similarity 0.94)
- 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 0.92)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · 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.