Research map / Detection and segmentation / Open-set and few-shot detection
X-Pose: Detecting Any Keypoints
Jie Yang, Ailing Zeng, 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 object-level alignment contrastive loss (ablation) | X-Pose · AP-10K | keypoint-level AP: 45.5 -> 72.6 | Improved |
| add keypoint-level alignment contrastive loss (ablation) | X-Pose · AP-10K | keypoint-level AP: 72.6 -> 73.2 | Improved |
| train with both visual and textual prompts rather than visual only (ablation) | X-Pose · AP-10K (visual test prompt) | keypoint-level AP: 71.5 -> 72.8 | Improved |
| train with both prompts rather than textual only (ablation) | X-Pose · AP-10K (textual test prompt) | keypoint-level AP: 72.9 -> 73.2 | Improved |
| add 5 animal datasets to training (ablation) | X-Pose · AnimalPose (unseen) | PCK: 52.7 -> 70.1 | Improved |
| add part-level, rigid and soft object datasets (ablation) | X-Pose · AP-10K keypoint AP | AP: AP-10K 74.2 -> 74.0; AnimalPose 70.1 -> 73.4 | Mixed |
| fine-tune GroundingDINO on keypoint datasets | GroundingDINO-T · COCO val | keypoint-level AP: 3.1 -> 1.8 | Hurt |
| use end-to-end X-Pose instead of top-down CLAMP in zero-shot setting | textual prompt keypoint detection · AP-10K train Bovidae test Canidae | AP: 46.9 -> 53.8 | Improved |
| use X-Pose instead of top-down SOTA on COCO | general keypoint detection · COCO val | AP: 78.6 -> 76.8 | Hurt |
| X-Pose versus CLIP for text-to-keypoint alignment | text-to-image alignment · AP-10K val keypoint | CLIP score: 21.75 -> 66.01 | Improved |
Later papers that compared with this method
1 later accepted paper reports X-Pose as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- GKDT: General Keypoint Detection Transformer (ECCV 2026 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation (ICLR 2025 · similarity 0.87)
- Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features (NeurIPS 2024 · similarity 0.87)
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 2025 · similarity 0.87)
- Detect Any Keypoints: An Efficient Light-Weight Few-Shot Keypoint Detector (AAAI 2024 · similarity 0.87)
- Meta-Point Learning and Refining for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.86)
- KeyPose: Category-Level 6D Object Pose Estimation with Self-Adaptive Keypoints (AAAI 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.
