Research map / Graph learning / Knowledge and temporal graphs
Bayesian Graph Convolution LSTM for Skeleton Based Action Recognition
Rui Zhao, Kang Wang, Hui Su, Qiang Ji
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 local-graph convolution (vs no graph) (ablation) | Bayesian GC-LSTM · UTD-MHAD | accuracy (%): 85.0 -> 87.2 | Improved |
| add global graph only (vs no graph) (ablation) | Bayesian GC-LSTM · UTD-MHAD | accuracy (%): 85.0 -> 81.5 | Hurt |
| combine local and global graphs (joint graph) (ablation) | Bayesian GC-LSTM · UTD-MHAD | accuracy (%): 87.2 -> 92.1 | Improved |
| mean-field graph (no edges) instead of no graph (ablation) | Bayesian GC-LSTM · UTD-MHAD | accuracy (%): 85.0 -> 82.2 | Hurt |
| LSTM instead of vanilla RNN (ablation) | Bayesian GC-LSTM · UTD-MHAD | accuracy (%): 66.4 -> 92.1 | Improved |
| LSTM instead of GRU (ablation) | Bayesian GC-LSTM · UTD-MHAD | accuracy (%): 89.7 -> 92.1 | Improved |
| stack two LSTM layers or use bi-directional LSTM (ablation) | Bayesian GC-LSTM · UTD-MHAD | accuracy (%): 92.1 -> 92.0 (stacked), 90.8 (bi-directional) | No clear effect |
| Bayesian inference instead of ML point estimate (clean) (ablation) | Bayesian GC-LSTM · UTD-MHAD clean | accuracy (%): 86.2 -> 87.4 | Improved |
| Bayesian inference instead of ML (rotation + noise) (ablation) | Bayesian GC-LSTM · UTD-MHAD rotation + noise | accuracy (%): 65.1 -> 82.8 | Improved |
| add prior (MAP instead of ML) under perturbation (ablation) | Bayesian GC-LSTM · UTD-MHAD rotation only | accuracy (%): 62.8 -> 78.1 | Improved |
| add adversarial prior to Bayesian inference (clean) (ablation) | Bayesian GC-LSTM · UTD-MHAD clean | accuracy (%): 87.4 -> 92.1 | Improved |
| add adversarial prior to Bayesian inference (rotation + noise) (ablation) | Bayesian GC-LSTM · UTD-MHAD rotation + noise | accuracy (%): 82.8 -> 85.9 | Improved |
Closest papers by meaning
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition (AAAI 2018 · similarity 0.92)
- An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition (CVPR 2019 · similarity 0.91)
- Graph CNNs with Motif and Variable Temporal Block for Skeleton-Based Action Recognition (AAAI 2019 · similarity 0.91)
- Learning Graph Convolutional Network for Skeleton-Based Human Action Recognition by Neural Searching (AAAI 2020 · similarity 0.91)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.89)
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition (AAAI 2024 · 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.
