Research map / Graph learning / Knowledge and temporal graphs
DDGCN: A Dynamic Directed Graph Convolutional Network for Action Recognition
Matthew Korban, Xin Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 Dynamic Convolutional Sampling (DCS) (ablation) | ST-GCN baseline · Kinect | top-1 accuracy: 30.7% -> 34.6% | Improved |
| add Dynamic Convolutional Weights (DCW) (ablation) | ST-GCN baseline · Kinect | top-1 accuracy: 30.7% -> 32.1% | Improved |
| add Directed Spatial-Temporal Graph features (DSTG) (ablation) | ST-GCN baseline · Kinect | top-1 accuracy: 30.7% -> 35.5% | Improved |
| combine DCS, DCW and DSTG (ablation) | ST-GCN baseline · Kinect | top-1 accuracy: 30.7% -> 38.12% | Improved |
| add DCS (ablation) | ST-GCN baseline · NTU-RGB+D Cross-Subject | accuracy: 81.5% -> 84.5% | Improved |
| add DCW (ablation) | ST-GCN baseline · NTU-RGB+D Cross-Subject | accuracy: 81.5% -> 81.9% | Improved |
| add DSTG (ablation) | ST-GCN baseline · NTU-RGB+D Cross-Subject | accuracy: 81.5% -> 85.4% | Improved |
| combine DCS, DCW and DSTG (ablation) | ST-GCN baseline · NTU-RGB+D Cross-Subject | accuracy: 81.5% -> 91.05% | Improved |
| add DCS (ablation) | ST-GCN baseline · NTU-RGB+D Cross-View | accuracy: 88.3% -> 90.3% | Improved |
| add DCW (ablation) | ST-GCN baseline · NTU-RGB+D Cross-View | accuracy: 88.3% -> 89.4% | Improved |
| add DSTG (ablation) | ST-GCN baseline · NTU-RGB+D Cross-View | accuracy: 88.3% -> 92.6% | Improved |
| combine DCS, DCW and DSTG (ablation) | ST-GCN baseline · NTU-RGB+D Cross-View | accuracy: 88.3% -> 97.14% | Improved |
Later papers that compared with this method
2 later accepted papers report DDGCN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection (AAAI 2024 · better on 3 of 3 shared results)
- Channel-Wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition (ICCV 2021 · better on 0 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (AAAI 2021 · similarity 0.89)
- Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition (CVPR 2019 · similarity 0.88)
- Are Spatial-Temporal Graph Convolution Networks for Human Action Recognition Over-Parameterized? (CVPR 2025 · similarity 0.88)
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition (AAAI 2024 · similarity 0.88)
- Action Recognition With Spatial-Temporal Discriminative Filter Banks (ICCV 2019 · similarity 0.88)
- Spatio-Temporal Fusion for Human Action Recognition via Joint Trajectory Graph (AAAI 2024 · similarity 0.87)
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.
