Research map / Graph learning / Knowledge and temporal graphs
Hierarchical Human Parsing With Typed Part-Relation Reasoning
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use hierarchical typed relation reasoning and iterative message passing | Hierarchical human parser · LIP val | Mean IoU: 57.74 -> 59.25 | Helped |
| Use hierarchical typed relation reasoning and iterative message passing | Hierarchical human parser · PASCAL-Person-Part test | mIoU: 70.76 -> 73.12 | Helped |
| Use hierarchical typed relation reasoning and iterative message passing | Hierarchical human parser · ATR test | F-1: 85.51 -> 87.25 | Helped |
| Use hierarchical typed relation reasoning and iterative message passing | Hierarchical human parser · Fashion Clothing test | F-1: 58.12 -> 60.19 | Helped |
| Use hierarchical typed relation reasoning and iterative message passing | Hierarchical human parser · PPSS test | mIoU: 60.5 -> 65.3 | Helped |
| Add structural relation information to initial node embeddings (ablation) | Hierarchical human parser · PASCAL-Person-Part test | mIoU: 68.84 -> 73.12 | Helped |
| Replace a shared relation model with relation-type-specific modeling (ablation) | Hierarchical human parser · PASCAL-Person-Part test | mIoU: 70.37 -> 71.65 | Helped |
| Add relation-adaption F^r to typed relation modeling (ablation) | Hierarchical human parser · PASCAL-Person-Part test | mIoU: 71.65 -> 73.12 | Helped |
| Use all three relation types instead of decomposition relation only (ablation) | Hierarchical human parser · PASCAL-Person-Part test | mIoU: 71.38 -> 73.12 | Helped |
| Use all three relation types instead of composition relation only (ablation) | Hierarchical human parser · PASCAL-Person-Part test | mIoU: 69.35 -> 73.12 | Helped |
| Use all three relation types instead of dependency relation only (ablation) | Hierarchical human parser · PASCAL-Person-Part test | mIoU: 69.43 -> 73.12 | Helped |
| Add message-passing inference rather than using zero iterations (ablation) | Hierarchical human parser · PASCAL-Person-Part test | mIoU: 68.84 -> 73.12 | Helped |
Closest papers by meaning
- Part-Aware Context Network for Human Parsing (CVPR 2020 · similarity 0.91)
- Graphonomy: Universal Human Parsing via Graph Transfer Learning (CVPR 2019 · similarity 0.89)
- Progressive Cognitive Human Parsing (AAAI 2018 · similarity 0.89)
- Grapy-ML: Graph Pyramid Mutual Learning for Cross-Dataset Human Parsing (AAAI 2020 · similarity 0.88)
- Self-Learning With Rectification Strategy for Human Parsing (CVPR 2020 · similarity 0.88)
- CDGNet: Class Distribution Guided Network for Human Parsing (CVPR 2022 · similarity 0.88)
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.