Research map / 3D vision / Human pose estimation
Learning Delicate Local Representations for Multi-Person Pose Estimation
Yuanhao Cai, Zhicheng Wang, Zhengxiong Luo, Binyi Yin, Angang Du, Haoqian Wang, Xiangyu Zhang, Xinyu Zhou, Erjin Zhou, Jian Sun
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 intra-level feature fusion (RSB) to ResNet-18 (ablation) | RSN-18 · COCO minival | AP: 72.9 -> 73.6 | Improved |
| add dense-sum branch connections instead of Baseline2 copies (ablation) | RSN-50 · COCO minival | AP: 72.7 -> 74.7 | Improved |
| replace ResNet-18 with RSN-18 | ResNet-18 · COCO minival | AP: 70.7 -> 73.6 | Improved |
| replace Res2Net-18 with RSN-18 | Res2Net-18 · COCO minival | AP: 71.3 -> 73.6 | Improved |
| use 4 branches instead of 2 in RSB (ablation) | RSN-18 · COCO minival | AP: 73.1 -> 73.6 | Improved |
| use 6 branches instead of 4 in RSB (ablation) | RSN-50 · COCO minival | AP: 74.7 -> 74.0 | Hurt |
| add Pose Refine Machine (ablation) | ResNet-18 · COCO minival | AP: 70.7 -> 72.2 | Improved |
| add Pose Refine Machine (ablation) | 4xRSN-50 · COCO minival | AP: 78.6 -> 79.0 | Improved |
| add SE-block attention instead of PRM (ablation) | ResNet-18 · COCO minival | AP: 70.7 -> 70.5 | Hurt |
| add CBAM attention instead of PRM (ablation) | ResNet-50 · COCO minival | AP: 72.2 -> 71.1 | Hurt |
| add SE-block attention to 4xRSN-50 (ablation) | 4xRSN-50 · COCO minival | AP: 78.6 -> 78.6 | No clear effect |
| use MegDet-v2 instead of MegDet as human detector (ablation) | 4xRSN-50 256x192 · COCO test-dev | AP: 77.3 -> 78.0 | Improved |
Closest papers by meaning
- Towards Accurate Multi-Person Pose Estimation in the Wild (CVPR 2017 · similarity 0.88)
- Cascaded Pyramid Network for Multi-Person Pose Estimation (CVPR 2018 · similarity 0.88)
- MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network (ECCV 2018 · similarity 0.88)
- Deep High-Resolution Representation Learning for Human Pose Estimation (CVPR 2019 · similarity 0.86)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.84)
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 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.
