Research map / 3D vision / Human pose estimation
Neural Interactive Keypoint Detection
Jie Yang, Ailing Zeng, Feng Li, Shilong Liu, Ruimao Zhang, Lei Zhang
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 pose error modeling training (ablation) | Click-Pose-C0 · COCO val | AP: 70.9 -> 72.1 AP; convergence 60e -> 45e | Improved |
| add interactive human-feedback loop training (ablation) | Click-Pose-C0 · COCO val | AP: 72.1 -> 73.0 | Improved |
| correct the worst keypoint instead of a random one (ablation) | Click-Pose · COCO val (2 clicks) | AP: 84.2 -> 90.3 | Improved |
| use progressive loop (one keypoint per iteration) instead of one-shot multi-keypoint modification (ablation) | Click-Pose · COCO val (4 clicks) | AP: 95.2 -> 96.4 | Improved |
| perturb keypoint position queries slightly at inference in ED-Pose decoder | ED-Pose · COCO val | AP: 71.6 -> 11.8 | Hurt |
| use Click-Pose with 3 clicks instead of ViTPose with manual correction | Click-Pose · Human-Art val (OOD) | AP: 32.1 -> 61.6 | Improved |
| interactive fine-tuning on 100 Human-Art images for new keypoints | Click-Pose-C0 · Human-Art (21 keypoints) | AP@21: 25.1 -> 47.1 | Improved |
| expand correctable keypoint range from 1-17 to 1-21 (ablation) | Click-Pose-C2 · Human-Art adaptation (1000 images) | AP@4: 45.4 -> 67.1 | Improved |
Closest papers by meaning
- Incremental Object Keypoint Learning (CVPR 2025 · similarity 0.84)
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 2025 · similarity 0.84)
- Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation (CVPR 2025 · similarity 0.84)
- KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension (NeurIPS 2024 · similarity 0.84)
- ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.84)
- Meta-Point Learning and Refining for Category-Agnostic Pose Estimation (CVPR 2024 · 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.
