# Deep Attributes Driven Multi-Camera Person Re-identification

arXiv: https://arxiv.org/abs/1605.03259 · HTML: https://mlsanity.com/paper/1605.03259/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2016.

## Built on by (most cited first, 21 of 21)

- [TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search](https://mlsanity.com/paper/2105.11628/) (2021)
- [Learning Conditional Attributes for Compositional Zero-Shot Learning](https://mlsanity.com/paper/2305.17940/) (2023)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning](https://mlsanity.com/paper/2302.11102/) (2023)
- [Consistency and Accuracy of CelebA Attribute Values](https://mlsanity.com/paper/2210.07356/) (2022)
- [Exploring the Quality of GAN Generated Images for Person Re-Identification](https://mlsanity.com/paper/2108.09977/) (2021)
- [Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysis](https://mlsanity.com/paper/2205.12144/) (2022)
- [Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization](https://mlsanity.com/paper/2106.06485/) (2021)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Graph Convolution for Re-ranking in Person Re-identification](https://mlsanity.com/paper/2107.02220/) (2021)
- [OpenAnimals: Revisiting Person Re-Identification for Animals Towards Better Generalization](https://mlsanity.com/paper/2410.00204/) (2024)
- [Large-Scale Attribute-Object Compositions](https://mlsanity.com/paper/2105.11373/) (2021)
- [Domain-Class Correlation Decomposition for Generalizable Person Re-Identification](https://mlsanity.com/paper/2106.15206/) (2021)
- [LogicNet: A Logical Consistency Embedded Face Attribute Learning Network](https://mlsanity.com/paper/2311.11208/) (2023)
- [Multi-Granularity Graph Pooling for Video-based Person Re-Identification](https://mlsanity.com/paper/2209.11584/) (2022)
- [Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person Retrieval](https://mlsanity.com/paper/2309.08372/) (2023)
- [E^2TAD: An Energy-Efficient Tracking-based Action Detector](https://mlsanity.com/paper/2204.04416/) (2022)
- [Advancing Person Re-Identification: Tensor-based Feature Fusion and Multilinear Subspace Learning](https://mlsanity.com/paper/2312.16226/) (2023)
- [Multilinear subspace learning for person re-identification based fusion of high order tensor features](https://mlsanity.com/paper/2505.15825/) (2025)
- [Enhancing Person Re-Identification through Tensor Feature Fusion](https://mlsanity.com/paper/2312.10470/) (2023)
- [Person Re-Identification System at Semantic Level based on Pedestrian Attributes Ontology](https://mlsanity.com/paper/2506.04143/) (2025)

## Abstract (arXiv)

The visual appearance of a person is easily affected by many factors like pose variations, viewpoint changes and camera parameter differences. This makes person Re-Identification (ReID) among multiple cameras a very challenging task. This work is motivated to learn mid-level human attributes which are robust to such visual appearance variations. And we propose a semi-supervised attribute learning framework which progressively boosts the accuracy of attributes only using a limited number of labeled data. Specifically, this framework involves a three-stage training. A deep Convolutional Neural Network (dCNN) is first trained on an independent dataset labeled with attributes. Then it is fine-tuned on another dataset only labeled with person IDs using our defined triplet loss. Finally, the updated dCNN predicts attribute labels for the target dataset, which is combined with the independent dataset for the final round of fine-tuning. The predicted attributes, namely deep attributes exhibit superior generalization ability across different datasets. By directly using the deep attributes with simple Cosine distance, we have obtained surprisingly good accuracy on four person ReID datasets. Experiments also show that a simple metric learning modular further boosts our method, making it significantly outperform many recent works.