Research map / Video / Video segmentation and tracking
LD-ConGR: A Large RGB-D Video Dataset for Long-Distance Continuous 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 |
|---|---|---|---|
| Fuse RGB and depth features with MMTM instead of using RGB alone | ResNeXt-101 · LD-ConGR test | accuracy: 85.33% -> 89.66% | Helped |
| Fuse RGB and depth features with MMTM instead of using RGB alone | ResNeXt-101 · LD-ConGR continuous gesture recognition | mean Jaccard Index: 0.31 -> 0.34 | Helped |
| Estimate and crop the gesture region (ablation) | LD-ConGR recognition model, 16-frame RGB input · LD-ConGR test | accuracy: 82.16 -> 92.02 | Helped |
| Estimate and crop the gesture region (ablation) | LD-ConGR recognition model, 16-frame RGB-D input · LD-ConGR test | accuracy: 86.00 -> 93.75 | Helped |
| Estimate and crop the gesture region (ablation) | LD-ConGR recognition model, 32-frame RGB input · LD-ConGR test | accuracy: 85.33 -> 94.66 | Helped |
| Estimate and crop the gesture region (ablation) | LD-ConGR recognition model, 32-frame RGB-D input · LD-ConGR test | accuracy: 89.66 -> 97.33 | Helped |
| Add key-frame sampling after gesture-region estimation (ablation) | LD-ConGR recognition model, 16-frame RGB input · LD-ConGR test | accuracy: 92.02 -> 93.26 | Helped |
| Add key-frame sampling after gesture-region estimation (ablation) | LD-ConGR recognition model, 16-frame RGB-D input · LD-ConGR test | accuracy: 93.75 -> 94.68 | Helped |
| Add key-frame sampling after gesture-region estimation (ablation) | LD-ConGR recognition model, 32-frame RGB input · LD-ConGR test | accuracy: 94.66 -> 94.62 | No clear effect |
| Add key-frame sampling after gesture-region estimation (ablation) | LD-ConGR recognition model, 32-frame RGB-D input · LD-ConGR test | accuracy: 97.33 -> 97.45 | No clear effect |
| Use the proposed method rather than TSN | LD-ConGR RGB recognition · LD-ConGR test | accuracy: 86.80 -> 94.66 | Helped |
| Use the proposed method rather than TPN-TSM | LD-ConGR RGB recognition · LD-ConGR test | accuracy: 87.45 -> 94.66 | Helped |
Closest papers by meaning
- Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition (AAAI 2021 · similarity 0.86)
- SocialGesture: Delving into Multi-person Gesture Understanding (CVPR 2025 · similarity 0.84)
- GigaHands: A Massive Annotated Dataset of Bimanual Hand Activities (CVPR 2025 · similarity 0.82)
- FSboard: Over 3 Million Characters of ASL Fingerspelling Collected via Smartphones (CVPR 2025 · similarity 0.82)
- Multi-Modal Hand-to-Mouth Gesture Recognition in Activity-Oriented RGB-Thermal Footage (Student Abstract) (AAAI 2025 · similarity 0.82)
- OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition (AAAI 2025 · similarity 0.82)
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.