Research map / Video / Action recognition
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition From Skeleton Data
Pengfei Zhang, Cuiling Lan, Junliang Xing, Wenjun Zeng, Jianru Xue, Nanning Zheng
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 learned view adaptation (rotation and translation) over S-trans+LSTM (ablation) | S-trans+LSTM · NTU RGB+D Cross-Subject | accuracy (%): 76.0 -> 79.4 | Improved |
| add learned view adaptation (rotation and translation) over S-trans+LSTM (ablation) | S-trans+LSTM · NTU RGB+D Cross-View | accuracy (%): 82.3 -> 87.6 | Improved |
| replace frame-level hand-defined translation and rotation with learned view adaptation (ablation) | F-trans&F-rota+LSTM · NTU RGB+D Cross-Subject | accuracy (%): 74.1 -> 79.4 | Improved |
| replace frame-level hand-defined translation and rotation with learned view adaptation (ablation) | F-trans&F-rota+LSTM · NTU RGB+D Cross-View | accuracy (%): 83.9 -> 87.6 | Improved |
| replace sequence-level hand-defined translation and rotation with learned view adaptation (ablation) | S-trans&S-rota+LSTM · NTU RGB+D Cross-Subject | accuracy (%): 76.4 -> 79.4 | Improved |
| replace sequence-level hand-defined translation and rotation with learned view adaptation (ablation) | S-trans&S-rota+LSTM · NTU RGB+D Cross-View | accuracy (%): 85.4 -> 87.6 | Improved |
| add learned rotation to translation-only view adaptation (ablation) | VA-LSTM · NTU RGB+D Cross-Subject | accuracy (%): 77.7 -> 79.4 | Improved |
| add learned rotation to translation-only view adaptation (ablation) | VA-LSTM · NTU RGB+D Cross-View | accuracy (%): 84.9 -> 87.6 | Improved |
| add learned translation to rotation-only view adaptation (ablation) | VA-LSTM · NTU RGB+D | accuracy (%): CS 79.4 -> 79.4; CV 87.1 -> 87.6 | No clear effect |
| add sequence-level translation to raw skeleton input (ablation) | Raw+LSTM · NTU RGB+D Cross-Subject | accuracy (%): 66.3 -> 76.0 | Improved |
| use sequence-level instead of frame-level translation (ablation) | LSTM with hand-defined preprocessing · NTU RGB+D Cross-Subject | accuracy (%): 75.1 -> 76.0 | Improved |
| use sequence-level instead of frame-level translation (ablation) | LSTM with hand-defined preprocessing · NTU RGB+D Cross-View | accuracy (%): 80.5 -> 82.3 | Improved |
Closest papers by meaning
- View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (TPAMI 2019 · similarity 0.96)
- Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (CVPR 2017 · similarity 0.91)
- Adaptive RNN Tree for Large-Scale Human Action Recognition (ICCV 2017 · similarity 0.90)
- An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data (AAAI 2017 · similarity 0.90)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.88)
- 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.
