Research map / 3D vision / Human pose estimation
Benchmarking and Error Diagnosis in Multi-Instance Pose Estimation
Matteo Ruggero Ronchi, Pietro Perona
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 |
|---|---|---|---|
| replace detection scores with optimal (oracle max-OKS) scores (ablation) | Cmu and Grmi · COCO keypoints | AP averaged over OKS thresholds: about 5% | Improved |
| replace detection scores with optimal scores at strict threshold (ablation) | Cmu and Grmi · COCO keypoints | AP at OKS .95: up to 10% | Improved |
| correct miss localization errors (ablation) | Cmu and Grmi · COCO keypoints | AP at OKS .75: ~15% | Improved |
| correct inversion localization errors (ablation) | Cmu and Grmi · COCO keypoints | AP at OKS .75: ~4% | Improved |
| correct jitter errors (ablation) | Cmu and Grmi · COCO keypoints | instance OKS | No clear effect |
| remove false negatives (ablation) | Cmu and Grmi · COCO keypoints | AP: about 40% | Improved |
| remove false positives (ablation) | Cmu and Grmi · COCO keypoints | AP: only 5% | Improved |
| replace Cmu scores with optimal scores: scoring errors and matches (ablation) | Cmu · COCO keypoints | matches: 64 more matches, 590 matches with OKS improvement | Improved |
| replace Grmi scores with optimal scores: scoring errors and matches (ablation) | Grmi · COCO keypoints | matches: 156 more matches, 430 matches with OKS improvement | Improved |
| increase instance size (ablation) | Cmu · COCO keypoints | AP | Mixed |
| fewer than 5 visible keypoints (ablation) | Cmu · COCO keypoints | annotations missed: over 30% | Hurt |
Closest papers by meaning
- Learning Quality-Aware Representation for Multi-Person Pose Regression (AAAI 2022 · similarity 0.89)
- Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation (AAAI 2020 · similarity 0.88)
- Towards Accurate Multi-Person Pose Estimation in the Wild (CVPR 2017 · similarity 0.88)
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 2025 · similarity 0.87)
- On the Calibration of Human Pose Estimation (ICML 2024 · similarity 0.86)
- RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges (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.
