Research map / Video / Action recognition
An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data
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 |
|---|---|---|---|
| add spatial and temporal attention | LSTM · SBU | accuracy (%): 86.72 -> 91.51 | Helped |
| add spatial attention (ablation) | LSTM · NTU Cross-Subject | accuracy (%): 66.80 -> 71.89 | Helped |
| add temporal attention (ablation) | LSTM · NTU Cross-Subject | accuracy (%): 66.80 -> 73.16 | Helped |
| add spatial and temporal attention | LSTM · NTU Cross-Subject | accuracy (%): 66.80 -> 73.42 | Helped |
| add spatial attention (ablation) | LSTM · NTU Cross-View | accuracy (%): 77.53 -> 80.35 | Helped |
| add temporal attention (ablation) | LSTM · NTU Cross-View | accuracy (%): 77.53 -> 80.51 | Helped |
| add spatial and temporal attention | LSTM · NTU Cross-View | accuracy (%): 77.53 -> 81.23 | Helped |
| add spatial attention regularization (ablation) | SA-LSTM · SBU, NTU Cross-Subject, NTU Cross-View | accuracy | Helped |
| add temporal attention regularization (ablation) | TA-LSTM · SBU, NTU Cross-Subject, NTU Cross-View | accuracy | Helped |
| add spatial attention (ablation) | LSTM · SBU | accuracy (%): 86.72 -> 88.00 | Helped |
| add temporal attention (ablation) | LSTM · SBU | accuracy (%): 86.72 -> 88.79 | Helped |
Closest papers by meaning
- An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition (CVPR 2019 · similarity 0.93)
- Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition (AAAI 2022 · similarity 0.91)
- Co-Occurrence Feature Learning for Skeleton Based Action Recognition Using Regularized Deep LSTM Networks (AAAI 2016 · similarity 0.91)
- InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition (CVPR 2022 · similarity 0.90)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.87)
- Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition (CVPR 2025 · 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.