Research map / Label-efficient and robust learning / Recognition and long-tail
Attribute Recognition by Joint Recurrent Learning of Context and Correlation
Jingya Wang, Xiatian Zhu, Shaogang Gong, Wei 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 encoder LSTM for intra-person attribute context (ablation) | JRL · PETA | mAP_cls: 83.45 -> 85.67 | Improved |
| add encoder LSTM for intra-person attribute context (ablation) | JRL · RAP | mAP_cls: 75.19 -> 77.81 | Improved |
| add inter-person similarity context from top-k exemplars (ablation) | JRL · PETA | mAP_cls: 85.02 -> 85.67 | Improved |
| add inter-person similarity context from top-k exemplars (ablation) | JRL · RAP | mAP_cls: 76.94 -> 77.81 | Improved |
| use ensemble of 10 attribute orders instead of average single-order model (ablation) | JRL · PETA | mAP_cls: 82.13 -> 85.67 | Improved |
| use ensemble of 10 attribute orders instead of average single-order model (ablation) | JRL · RAP | mAP_cls: 74.74 -> 77.81 | Improved |
| add recurrent attribute attention (ablation) | JRL · PETA | mAP_cls: 84.03 -> 85.67 | Improved |
| add recurrent attribute attention (ablation) | JRL · RAP | mAP_cls: 75.96 -> 77.81 | Improved |
| use JRL instead of DeepMAR with 25% of training data | JRL vs DeepMAR · PETA | mAP_cls: mAP drop 3.64% vs 6.23% from 100% to 25% data | Improved |
| use JRL instead of DeepMAR with 25% of training data | JRL vs DeepMAR · RAP | mAP_cls: mAP drop 3.55% vs 5.73% from 100% to 25% data | Improved |
| use JRL instead of ACN on RAP precision | JRL vs ACN · RAP | mPrc_ins: 80.12% vs 78.11% | Hurt |
| use JRL instead of SR CNN-RNN | JRL vs SR CNN-RNN · PETA | mAP_cls: 82.83 -> 85.67 | Improved |
Closest papers by meaning
- Recurrent Attention Model for Pedestrian Attribute Recognition (AAAI 2019 · similarity 0.92)
- Pedestrian Attribute Recognition: A New Benchmark Dataset and a Large Language Model Augmented Framework (AAAI 2025 · similarity 0.87)
- Pedestrian Attribute Recognition as Label-balanced Multi-label Learning (ICML 2024 · similarity 0.87)
- Selective and Orthogonal Feature Activation for Pedestrian Attribute Recognition (AAAI 2024 · similarity 0.85)
- Enhanced Visual-Semantic Interaction with Tailored Prompts for Pedestrian Attribute Recognition (CVPR 2025 · similarity 0.84)
- Attribute-Guided Pedestrian Retrieval: Bridging Person Re-ID with Internal Attribute Variability (CVPR 2024 · similarity 0.84)
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.
