Research map / Graph learning / Knowledge and temporal graphs
Visual-Semantic Graph Reasoning for Pedestrian Attribute Recognition
Qiaozhe Li, Xin Zhao, Ran He, Kaiqi Huang
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 spatial graph (GCN over regions) on ResNet-50 (ablation) | ResNet-50 · PETA | mA: 81.27 -> 81.65 | Improved |
| add spatial graph (GCN over regions) on ResNet-50 (ablation) | ResNet-50 · RAP | mA: 75.12 -> 75.54 | Improved |
| add spatial graph (GCN over regions) on ResNet-50 (ablation) | ResNet-50 · PA-100k | mA: 76.31 -> 77.05 | Improved |
| add directed semantic graph for sequential prediction (ablation) | ResNet-50 · PETA | mA: 81.27 -> 83.85 | Improved |
| add directed semantic graph for sequential prediction (ablation) | ResNet-50 · PA-100k | mA: 76.31 -> 78.54 | Improved |
| add semantic-to-visual mutual embedding and combine both sub-networks (full) over Gs->e only (ablation) | visual-semantic graph reasoning · PETA | mA: 84.96 -> 85.21 | Improved |
| combine both sub-networks over Ge->s only (ablation) | visual-semantic graph reasoning · RAP | F1: 79.94 -> 81.34 | Improved |
| add spatial graph alone (ablation) | ResNet-50 · RAP | F1: 79.00 -> 78.78 | No clear effect |
| full visual-semantic model vs ResNet-50 baseline | ResNet-50 · PA-100k | F1: 85.84 -> 88.26 | Improved |
| visual-semantic graph reasoning vs prior best JRL | PETA · PETA | mA: 85.67 -> 85.21 | Hurt |
| visual-semantic graph reasoning vs prior best MsVAA | pedestrian attribute recognition · PETA | F1: 86.46 -> 88.42 | Improved |
Closest papers by meaning
- Relation-Aware Pedestrian Attribute Recognition with Graph Convolutional Networks (AAAI 2020 · similarity 0.93)
- Learning Disentangled Attribute Representations for Robust Pedestrian Attribute Recognition (AAAI 2022 · similarity 0.89)
- Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework (AAAI 2025 · similarity 0.87)
- Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition (AAAI 2024 · similarity 0.85)
- Pedestrian Attribute Recognition as Label-balanced Multi-label Learning (ICML 2024 · similarity 0.84)
- Enhanced Visual-Semantic Interaction with Tailored Prompts for Pedestrian Attribute Recognition (CVPR 2025 · similarity 0.83)
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.
