Research map / Detection and segmentation / Tracking
Whose Hands Are These? Hand Detection and Hand-Body Association in the Wild
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 the Hand-Body Association Network to MaskRCNN | MaskRCNN · BodyHands test | Joint AP: 51.74 -> 63.48 | Helped |
| add the Hand-Body Association Network to MaskRCNN | MaskRCNN · COCO-WholeBody | Joint AP: 53.08 -> 62.87 | Helped |
| allow a detected hand to match to itself | Proposed hand-body association method · BodyHands test | Joint AP: 63.48 -> 63.87 | Helped |
| allow a detected hand to match to itself | Proposed hand-body association method · COCO-WholeBody | Joint AP: 62.87 -> 62.92 | Helped |
| add the Overlap Estimation Module (ablation) | Proposed hand-body association method · BodyHands test | Joint AP: 59.03% -> 63.48 | Helped |
| add the Positional Density Module (ablation) | Proposed hand-body association method · BodyHands test | Joint AP: 50.29% -> 63.48 | Helped |
| learn overlap with the Overlap Estimation Module rather than computing it from boxes (ablation) | Proposed hand-body association method · BodyHands test | Joint AP: 60.34 % -> 63.48 | Helped |
| use hand-body association to link tracks instead of hand-only IoU | hand tracking · YoutubeHands-20 | MOTA: 46.1 -> 50.0 | Helped |
| use hand-body association to link tracks instead of pose-based linking | hand tracking · YoutubeHands-20 | MOTA: 46.8 -> 50.0 | Helped |
| use a heuristic informed by hand-body association | pre-trained hand-contact network · ContactHands test | Person-Contact AP: 39.51% -> 40.89% | Helped |
| jointly estimate contact state and associate hands with bodies | hand contact estimation network · ContactHands test | Person-Contact AP: 39.51% -> 47.09% | Helped |
Closest papers by meaning
- Detecting Hands and Recognizing Physical Contact in the Wild (NeurIPS 2020 · similarity 0.90)
- Forward Propagation, Backward Regression, and Pose Association for Hand Tracking in the Wild (CVPR 2022 · similarity 0.89)
- Analysis of Hand Segmentation in the Wild (CVPR 2018 · similarity 0.88)
- SiMHand: Mining Similar Hands for Large-Scale 3D Hand Pose Pre-training (ICLR 2025 · similarity 0.87)
- Learning Dense Hand Contact Estimation from Imbalanced Data (NeurIPS 2025 · similarity 0.86)
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (CVPR 2025 · similarity 0.86)
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.