Research map / 3D vision / Human pose estimation
LDPose: Towards Inclusive Human Pose Estimation for Limb-Deficient Individuals in the Wild
Jiaying Ying, Heming Du, Kaihao Zhang, Lincheng Li, Xin Yu
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 |
|---|---|---|---|
| fine-tune on LDPose training set | YOLO-Pose csp-d53-s · LDPose, COCO Metrics | AP: 42.6 -> 49.8 | Improved |
| fine-tune on LDPose training set | RTMPose CSPNeXt-s · LDPose, COCO Metrics | AP: 69.1 -> 77.1 | Improved |
| fine-tune on LDPose training set | ViTPose ViT-l · LDPose, COCO Metrics | AP: 80.0 -> 82.6 | Improved |
| add LDLoss (ablation) | ViTPose ViT-l fine-tuned · LDPose, LD Metrics | AP: 75.5 -> 78.4 | Improved |
| add LDLoss (ablation) | RTMPose CSPNeXt-s fine-tuned · LDPose, LD Metrics | AP: 61.8 -> 69.5 | Improved |
| add LDLoss (ablation) | ViTPose ViT-b fine-tuned · LDPose, LD Metrics | AP: 69.6 -> 75.9 | Improved |
| add LDLoss (ablation) | RTMPose CSPNeXt-l fine-tuned · LDPose, COCO Metrics | AP: 80.8 -> 74.9 | Hurt |
| add LDLoss (ablation) | ViTPose ViT-l fine-tuned · LDPose, COCO Metrics | AP: 82.6 -> 80.9 | Hurt |
| add LDLoss (ablation) | ViTPose ViT-b fine-tuned · LDPose, COCO Metrics | AP: 78.2 -> 78.9 | Improved |
| add LDLoss (ablation) | YOLO-Pose csp-d53-l fine-tuned · LDPose, COCO Metrics | AP: 51.9 -> 50.9 | Hurt |
| add LDLoss (ablation) | YOLO-Pose csp-d53-s fine-tuned · LDPose, COCO Metrics | AP: 49.8 -> 49.9 | No clear effect |
Closest papers by meaning
- InclusiveVidPose: Bridging the Pose Estimation Gap for Individuals with Limb Deficiencies in Video-Based Motion (ICLR 2026 · similarity 0.94)
- FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions (CVPR 2024 · similarity 0.85)
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 2025 · similarity 0.85)
- FlexPose: Pose Distribution Adaptation with Limited Guidance (AAAI 2025 · similarity 0.85)
- Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors (CVPR 2024 · similarity 0.84)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.84)
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.
