Research map / 3D vision / 3D generation
Decoupled Representation Learning for Skeleton-Based Gesture 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 |
|---|---|---|---|
| Add HMM and FRPV to HPEV (ablation) | HPEV gesture recognition · SHREC’17 Track, 14 gestures | accuracy: 73.45 -> 94.88 | Helped |
| Add HMM and FRPV to HPEV (ablation) | HPEV gesture recognition · SHREC’17 Track, 28 gestures | accuracy: 71.43 -> 92.26 | Helped |
| Add HMM and FRPV to HPEV (ablation) | HPEV gesture recognition · FPHA | accuracy: 77.04 -> 90.96 | Helped |
| Add FRPV to HPEV+HMM (ablation) | Two-stream gesture recognizer · FPHA | accuracy: 82.96 -> 90.96 | Helped |
| Add FRPV to HPEV+HMM (ablation) | Two-stream gesture recognizer · SHREC’17 Track, 14 gestures | accuracy: 94.40 -> 94.88 | Helped |
| Add FRPV to HPEV+HMM (ablation) | Two-stream gesture recognizer · SHREC’17 Track, 28 gestures | accuracy: 90.24 -> 92.26 | Helped |
| Replace HPEM with HPEV (ablation) | HPEM+HMM+FRPV · SHREC’17 Track, 14 gestures | accuracy: 92.85 -> 94.88 | Helped |
| Replace HPEM with HPEV (ablation) | HPEM+HMM+FRPV · SHREC’17 Track, 28 gestures | accuracy: 90.35 -> 92.26 | Helped |
| Replace HPEM with HPEV (ablation) | HPEM+HMM+FRPV · FPHA | accuracy: 85.74 -> 90.96 | Helped |
| Use a nonzero skeleton gap in HPEV (ablation) | HPEV · SHREC’17 Track, 14 gestures | accuracy: 62.26 -> 73.45 | Helped |
| Set HPEV skeleton gap to 3 (ablation) | HPEV+HMM+FRPV · SHREC’17 Track, 14 gestures | accuracy: 93.10 -> 94.88 | Helped |
| Use the full decoupled method instead of DG-STA | SHREC’17 Track, 14 gestures · SHREC’17 Track, 14 gestures | accuracy: 94.40 -> 94.88 | Helped |
Closest papers by meaning
- Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition (NeurIPS 2025 · similarity 0.87)
- Heterogeneous Skeleton-Based Action Representation Learning (CVPR 2025 · similarity 0.84)
- Forecasting of 3D Whole-body Human Poses with Grasping Objects (CVPR 2024 · similarity 0.84)
- How Do I Do That? Synthesizing 3D Hand Motion and Contacts for Everyday Interactions (CVPR 2025 · similarity 0.84)
- BOTH2Hands: Inferring 3D Hands from Both Text Prompts and Body Dynamics (CVPR 2024 · similarity 0.83)
- Hand1000: Generating Realistic Hands from Text with Only 1,000 Images (AAAI 2025 · similarity 0.83)
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.