Research map / 3D vision / Human pose estimation
Attribute And-Or Grammar for Joint Parsing of Human Pose, Parts and Attributes
Seyoung Park, Bruce Xiaohan Nie, Song Chun Zhu
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 pose inference to attribute prediction (ablation) | A-AOG (8 layers) · Attributes of People (no GT box) | mAP: 81.6 -> 84.2 | Improved |
| add pose inference to attribute prediction (ablation) | A-AOG (16 layers) · Attributes of People (no GT box) | mAP: 85.8 -> 88.5 | Improved |
| add or-nodes to the joint model (ablation) | A-AOG (8 layers) · Attributes of People (no GT box) | mAP: 84.2 -> 85.6 | Improved |
| add or-nodes to the joint model (ablation) | A-AOG (16 layers) · Attributes of People (no GT box) | mAP: 88.5 -> 89.4 | Improved |
| add or-nodes to the joint model (ablation) | A-AOG (8 layers) · Attributes of People (GT box) | mAP: 86.7 -> 87.7 | Improved |
| add or-nodes to the joint model (ablation) | A-AOG (16 layers) · Attributes of People (GT box) | mAP: 90.7 -> 91.6 | Improved |
| add pose inference to attribute prediction (ablation) | A-AOG · Pedestrian attribute dataset | mAC: 80.8 -> 84.3 | Improved |
| add or-nodes to the joint model (ablation) | A-AOG · Pedestrian attribute dataset | mAC: 84.3 -> 85.5 | Improved |
| add attribute constraints to pose estimation (ablation) | A-AOG · Attributes of People pose (no GT box) | PCP avg: 46.7 -> 51.3 | Improved |
| add or-nodes to pose estimation model (ablation) | A-AOG · Attributes of People pose (no GT box) | PCP avg: 51.3 -> 52.5 | Improved |
| add or-nodes to pose estimation model (ablation) | A-AOG · Attributes of People pose (GT box) | PCP avg: 52.0 -> 52.4 | Improved |
| use joint attribute-conditioned pose instead of per-part max over proposals (ablation) | A-AOG pose estimation · Attributes of People pose (no GT box) | PCP: decreased by 4.6% point | Improved |
Closest papers by meaning
- Look into Person: Joint Body Parsing & Pose Estimation Network and a New Benchmark (TPAMI 2018 · similarity 0.89)
- Pose-Guided Human Parsing by an AND/OR Graph Using Pose-Context Features (AAAI 2016 · similarity 0.89)
- Parsing Based on Parselets: A Unified Deformable Mixture Model for Human Parsing (TPAMI 2016 · similarity 0.88)
- Correlating Edge, Pose With Parsing (CVPR 2020 · similarity 0.87)
- Neural Architecture Search for Joint Human Parsing and Pose Estimation (ICCV 2021 · similarity 0.87)
- Hierarchical Human Semantic Parsing with Comprehensive Part-Relation Modeling (TPAMI 2021 · 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.
