Research map / Graph learning / Knowledge and temporal graphs
Relation-Aware Pedestrian Attribute Recognition with Graph Convolutional Networks
Zichang Tan, Yang Yang, Jun Wan, Guodong Guo, Stan Z. Li
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 Attribute Relation Module (ARM) (ablation) | PAR baseline · PETA | mA: 84.81 -> 85.75 | Improved |
| add ARM (ablation) | PAR baseline · RAP | mA: 80.49 -> 82.86 | Improved |
| add Contextual Relation Module (CRM) (ablation) | PAR baseline · RAP | mA: 80.49 -> 83.20 | Improved |
| add CRM (ablation) | PAR baseline · PA-100K | mA: 81.17 -> 81.84 | Improved |
| add CRM to PAR+ARM (ablation) | PAR + ARM · PA-100K | mA: 82.31 -> 82.10 | Hurt |
| add BN in classifiers (ablation) | PAR + ARM + CRM · PETA | mA: 86.03 -> 86.96 | Improved |
| GCN instead of LSTM (ablation) | ARM · PETA | mean of five criteria: 84.65 -> 84.95 | Improved |
| GCN instead of LSTM (ablation) | CRM · PETA | mean of five criteria: 84.53 -> 85.03 | Improved |
| use both L_A,cons and L_A losses vs only one (ablation) | ARM · PETA | mA | Improved |
| JLAC vs JLPLS-PAA | pedestrian attribute recognition · PETA | mA: 84.88 -> 86.96 | Improved |
| JLAC vs CoCNN | pedestrian attribute recognition · RAP | mA: 81.42 -> 83.69 | Improved |
Closest papers by meaning
- Visual-Semantic Graph Reasoning for Pedestrian Attribute Recognition (AAAI 2019 · similarity 0.93)
- Attribute Recognition by Joint Recurrent Learning of Context and Correlation (ICCV 2017 · similarity 0.90)
- Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework (AAAI 2025 · similarity 0.86)
- 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 0.83)
- 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.
