Research map / Video / Action recognition
An Attention Enhanced Graph Convolutional LSTM Network 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 LSTM with graph-convolutional recurrent units (ablation) | AGC-LSTM architecture · NTU RGB+D Cross-View | accuracy: 89.4 -> 92.4 | Helped |
| Replace LSTM with graph-convolutional recurrent units (ablation) | AGC-LSTM architecture · NTU RGB+D Cross-Subject | accuracy: 80.3 -> 85.6 | Helped |
| Add temporal hierarchical architecture (ablation) | LSTM · NTU RGB+D Cross-View | accuracy: 89.4 -> 90.4 | Helped |
| Add temporal hierarchical architecture (ablation) | GC-LSTM · NTU RGB+D Cross-View | accuracy: 92.4 -> 92.9 | Helped |
| Add temporal hierarchical architecture (ablation) | LSTM · Northwestern-UCLA | accuracy: 70.0 -> 78.5 | Helped |
| Add temporal hierarchical architecture (ablation) | GC-LSTM · Northwestern-UCLA | accuracy: 87.5 -> 89.4 | Helped |
| Add spatial attention (ablation) | GC-LSTM+TH · NTU RGB+D Cross-View | accuracy: 92.9 -> 93.5 | Helped |
| Add spatial attention (ablation) | GC-LSTM+TH · NTU RGB+D Cross-Subject | accuracy: 86.3 -> 87.5 | Helped |
| Add spatial attention (ablation) | GC-LSTM+TH · Northwestern-UCLA | accuracy: 89.4 -> 92.2 | Helped |
| Fuse joint- and part-based AGC-LSTM models (ablation) | AGC-LSTM · NTU RGB+D Cross-View | accuracy: 93.5 -> 95.0 | Helped |
| Fuse joint- and part-based AGC-LSTM models (ablation) | AGC-LSTM · Northwestern-UCLA | accuracy: 92.2 -> 93.3 | Helped |
| Use the part-based rather than joint-based input representation (ablation) | AGC-LSTM · Northwestern-UCLA | accuracy: 92.2 -> 90.1 | Hurt |
Closest papers by meaning
- Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition (AAAI 2021 · similarity 0.93)
- An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data (AAAI 2017 · similarity 0.93)
- Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition (AAAI 2018 · similarity 0.92)
- Learning Graph Convolutional Network for Skeleton-Based Human Action Recognition by Neural Searching (AAAI 2020 · similarity 0.92)
- Dynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition (AAAI 2024 · similarity 0.91)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (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.