Research map / Video / Action recognition
Adaptive RNN Tree for Large-Scale Human Action Recognition
Wenbo Li, Longyin Wen, Ming-Ching Chang, Ser Nam Lim, Siwei Lyu
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 early jump-out of recognized classes (ablation) | HBRNN-L-T · 3D-SAR-140 | accuracy: 0.700 -> 0.756 | Improved |
| add inefficiency penalization (ablation) | HBRNN-L-T · 3D-SAR-140 | accuracy: 0.697 -> 0.756 | Improved |
| add joint fine-tuning of RNNs (ablation) | HBRNN-L-T · 3D-SAR-140 | accuracy: 0.733 -> 0.756 | Improved |
| increase tree levels from 1 to 2 (ablation) | HBRNN-L-T · 3D-SAR-140 | accuracy: 0.604 -> 0.735 | Improved |
| increase tree levels from 2 to 3 (ablation) | HBRNN-L-T · 3D-SAR-140 | accuracy: 0.735 -> 0.750 | Improved |
| increase tree levels from 3 to 4 (ablation) | HBRNN-L-T · 3D-SAR-140 | accuracy: 0.750 -> 0.756 | Improved |
| allow overlapping action categories (theta_o 0.2 vs 1 which gives plain decision tree) (ablation) | RNN-T/ACH · 3D-SAR-140 | accuracy | Improved |
| wrap URNN-2L in RNN tree | URNN-2L · 3D-SAR-140 | accuracy: 0.866 -> 0.892 | Improved |
| wrap HBRNN-L in RNN tree | HBRNN-L · 3D-SAR-140 | accuracy: 0.604 -> 0.756 | Improved |
| wrap URNN in RNN tree | URNN · 3D-SAR-140 | accuracy: 0.296 -> 0.539 | Improved |
| wrap URNN-2L in RNN tree | URNN-2L · NTU RGB+D cross-view | accuracy: 0.809 -> 0.832 | Improved |
| wrap URNN-2L in RNN tree | URNN-2L · NTU RGB+D cross-subject | accuracy: 0.730 -> 0.746 | Improved |
Closest papers by meaning
- View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition From Skeleton Data (ICCV 2017 · similarity 0.90)
- View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (TPAMI 2019 · similarity 0.90)
- Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (CVPR 2017 · similarity 0.90)
- Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition (CVPR 2019 · similarity 0.89)
- RPAN: An End-To-End Recurrent Pose-Attention Network for Action Recognition in Videos (ICCV 2017 · similarity 0.89)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.88)
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.
