Research map / 3D vision / Human pose estimation
Neural Architecture Search for Joint Human Parsing and Pose Estimation
Dan Zeng, Yuhang Huang, Qian Bao, Junjie Zhang, Chi Su, Wu Liu
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 searched encoder-decoder (ablation) | ResNet50+FPN baseline · LIP val | mIoU: 46.72 -> 51.13 | Improved |
| add searched encoder-decoder (ablation) | ResNet50+FPN baseline · LIP val | PCK: 84.0 -> 85.6 | Improved |
| add feature interaction search (ablation) | baseline · LIP val | mIoU: 46.72 -> 50.31 | Improved |
| add feature interaction search (ablation) | baseline · LIP val | PCK: 84.0 -> 85.7 | Improved |
| add feature interaction search (ablation) | searched encoder-decoder · LIP val | mIoU: 51.13 -> 55.74 | Improved |
| add feature interaction search (ablation) | searched encoder-decoder · LIP val | PCK: 85.6 -> 87.6 | Improved |
| add feature fusion search (ablation) | baseline · LIP val | mIoU: 46.72 -> 48.05 | Improved |
| add feature fusion search (ablation) | baseline · LIP val | PCK: 84.0 -> 85.2 | Improved |
| add feature fusion search (ablation) | searched encoder-decoder · LIP val | mIoU: 51.13 -> 53.58 | Improved |
| add feature fusion search (ablation) | encoder-decoder + interaction · LIP val | mIoU: 55.74 -> 57.14 | Improved |
| add feature fusion search (ablation) | encoder-decoder + interaction · LIP val | PCK: 87.6 -> 88.3 | Improved |
| add searched encoder-decoder (ablation) | interaction + fusion · LIP val | mIoU: 52.03 -> 57.14 | Improved |
Closest papers by meaning
- Attribute And-Or Grammar for Joint Parsing of Human Pose, Parts and Attributes (TPAMI 2017 · similarity 0.87)
- Mutual Learning to Adapt for Joint Human Parsing and Pose Estimation (ECCV 2018 · similarity 0.87)
- Look into Person: Joint Body Parsing & Pose Estimation Network and a New Benchmark (TPAMI 2018 · similarity 0.87)
- ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search (CVPR 2021 · similarity 0.87)
- On the Correlation among Edge, Pose and Parsing (TPAMI 2021 · similarity 0.86)
- Human Pose Estimation With Parsing Induced Learner (CVPR 2018 · 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.
