Research map / 3D vision / Human pose estimation
CapeNext: Rethinking and Refining Dynamic Support Information for Category-Agnostic Pose Estimation
Yu Zhu, Dan Zeng, Shuiwang Li, Qijun Zhao, Qiaomu Shen, Bo Tang
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 HCMI module (ablation) | CapeNext · MP-100 1-shot (avg of 5 splits) | PCK@0.2: 86.81 -> 88.37 | Improved |
| add DSFR module (ablation) | CapeNext · MP-100 1-shot (avg of 5 splits) | PCK@0.2: 84.25 -> 88.37 | Improved |
| add learnable weights (LW) (ablation) | CapeNext · MP-100 1-shot (avg of 5 splits) | PCK@0.2: 88.28 -> 88.37 | No clear effect |
| add image embedding to CapeX baseline (ablation) | CapeX · MP-100 1-shot (avg of 5 splits) | PCK@0.2: 87.61 -> 88.15 | Improved |
| add class embedding on top of image embedding (ablation) | CapeNext · MP-100 1-shot (avg of 5 splits) | PCK@0.2: 88.15 -> 88.37 | Improved |
| add gating (LW) under noisy class prompts (ablation) | CapeNext · MP-100 noisy class prompts | PCK@0.2: 87.58 -> 88.15 | Improved |
| use CapeNext instead of CapeX under typo keypoint prompts | CapeX · MP-100 keypoint typo | PCK@0.2: 64.10 -> 66.35 | Improved |
| use CapeNext instead of CapeX under paw->foreleg prompts | CapeX · MP-100 paw->foreleg | PCK@0.2: 86.77 -> 87.30 | Improved |
| use CapeNext with Swinv2-T instead of CapeX | CapeX · MP-100 1-shot | PCK@0.2: 87.61 -> 88.37 | Improved |
| use CapeNext with HRNet-w32 instead of CapeX | CapeX · MP-100 1-shot | PCK@0.2: 85.2 -> 86.3 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CapeX — CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation (ICLR 2025) · better on 12 of 12 shared results
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 0.90)
- ESCAPE: Encoding Super-keypoints for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.90)
- Meta-Point Learning and Refining for Category-Agnostic Pose Estimation (CVPR 2024 · similarity 0.90)
- SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation (CVPR 2024 · similarity 0.87)
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.86)
- Universal Features Guided Zero-Shot Category-Level Object Pose Estimation (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.
