Research map / 3D vision / Human pose estimation
Multi-Scale Structure-Aware Network for Human Pose Estimation
Lipeng Ke, Ming-Ching Chang, Honggang Qi, Siwei Lyu
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 multi-scale supervision at deconv layers (ablation) | Newell hourglass · MPII validation (ablation, PCKh 0.5) | PCKh: 87.1 -> 87.6 | Improved |
| add multi-scale regression network after MSS-net (ablation) | MSS-net · MPII validation (ablation, PCKh 0.5) | PCKh: 87.6 -> 88.1 | Improved |
| add structure-aware loss (ablation) | MSS-net + MSR-net · MPII validation (ablation, PCKh 0.5) | PCKh: 88.1 -> 88.3 | Improved |
| add keypoint masking fine-tuning (ablation) | MSS-net + MSR-net with structure-aware loss · MPII validation (ablation, PCKh 0.5) | PCKh: 88.3 -> 88.4 | Improved |
| use full multi-scale structure-aware network instead of Newell hourglass with multi-scale testing | Newell hourglass · MPII test (PCKh 0.5) | total PCKh: 90.9 -> 92.1 | Improved |
| use full network instead of Newell hourglass | Newell hourglass · FLIC (PCK 0.2) | wrist PCK: 97.0 -> 97.3 | Improved |
Closest papers by meaning
- Deep Dual Consecutive Network for Human Pose Estimation (CVPR 2021 · similarity 0.90)
- Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation (ICCV 2017 · similarity 0.90)
- 3D Human Pose Estimation Using Spatio-Temporal Networks with Explicit Occlusion Training (AAAI 2020 · similarity 0.89)
- Stacked Hourglass Networks for Human Pose Estimation (ECCV 2016 · similarity 0.88)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.88)
- PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation (CVPR 2025 · similarity 0.87)
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.
