Research map / Architectures and efficiency / Attention and transformers
Recurrent Attention Model for Pedestrian Attribute Recognition
Xin Zhao, Liufang Sang, Guiguang Ding, Jungong Han, Na Di, Chenggang Yan
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 |
|---|---|---|---|
| order attribute-group prediction global to local instead of random (ablation) | RC · PETA | mA: 85.05 -> 85.78 | Improved |
| order attribute-group prediction global to local instead of random (ablation) | RC · RAP | mA: 76.75 -> 78.47 | Improved |
| order attribute-group prediction global to local instead of random (ablation) | RC · RAP | recall: 77.77 -> 76.65 | Hurt |
| order attribute-group prediction global to local instead of random (ablation) | RA · PETA | mA: 85.54 -> 86.11 | Improved |
| order attribute-group prediction global to local instead of random (ablation) | RA · RAP | F1: 79.09 -> 79.34 | Improved |
| RA vs RC (add recurrent spatial attention) | RC · RAP | mA: 78.47 -> 81.16 | Improved |
| RA vs RC (add recurrent spatial attention) | RC · PETA | F1: 86.70 -> 86.56 | No clear effect |
| RA vs SR CNN-RNN | SR CNN-RNN · RAP | mA: 74.21 -> 81.16 | Improved |
| RA vs JRL* ensemble | JRL* · PETA | mA: 85.67 -> 86.11 | Improved |
Closest papers by meaning
- Attribute Recognition by Joint Recurrent Learning of Context and Correlation (ICCV 2017 · similarity 0.92)
- Relation-Aware Pedestrian Attribute Recognition with Graph Convolutional Networks (AAAI 2020 · similarity 0.88)
- 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 0.86)
- 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.
