# Person Re-identification by Saliency Learning

arXiv: https://arxiv.org/abs/1412.1908 · HTML: https://mlsanity.com/paper/1412.1908/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2014.

## Built on by (most cited first, 20 of 20)

- [Specificity-preserving RGB-D Saliency Detection](https://mlsanity.com/paper/2108.08162/) (2021)
- [Person Re-identification: A Retrospective on Domain Specific Open Challenges and Future Trends](https://mlsanity.com/paper/2202.13121/) (2022)
- [Motion-aware Memory Network for Fast Video Salient Object Detection](https://mlsanity.com/paper/2208.00946/) (2022)
- [ViSaRL: Visual Reinforcement Learning Guided by Human Saliency](https://mlsanity.com/paper/2403.10940/) (2024)
- [Unifying Global-Local Representations in Salient Object Detection with Transformer](https://mlsanity.com/paper/2108.02759/) (2021)
- [Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2307.12917/) (2023)
- [GroupTransNet: Group Transformer Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2203.10785/) (2022)
- [A Mutual Learning Method for Salient Object Detection with intertwined Multi-Supervision--Revised](https://mlsanity.com/paper/2509.21363/) (2025)
- [LeNo: Adversarial Robust Salient Object Detection Networks with Learnable Noise](https://mlsanity.com/paper/2210.15392/) (2022)
- [Exploiting Robust Unsupervised Video Person Re-identification](https://mlsanity.com/paper/2111.05170/) (2021)
- [Skeleton Prototype Contrastive Learning with Multi-Level Graph Relation Modeling for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2208.11814/) (2022)
- [SiCL: Silhouette-Driven Contrastive Learning for Unsupervised Person Re-Identification with Clothes Change](https://mlsanity.com/paper/2305.13600/) (2023)
- [Attention-Guided Lidar Segmentation and Odometry Using Image-to-Point Cloud Saliency Transfer](https://mlsanity.com/paper/2308.14332/) (2023)
- [Dynamic Knowledge Distillation With Noise Elimination for RGB-D Salient Object Detection](https://mlsanity.com/paper/2106.09517/) (2021)
- [A Multi-parameter Updating Fourier Online Gradient Descent Algorithm for Large-scale Nonlinear Classification](https://mlsanity.com/paper/2203.08349/) (2022)
- [Dynamic Message Propagation Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2206.09552/) (2022)
- [Unleashing the Potential of Tracklets for Unsupervised Video Person Re-Identification](https://mlsanity.com/paper/2406.14261/) (2024)
- [The Research of Group Re-identification from Multiple Cameras](https://mlsanity.com/paper/2407.14620/) (2024)
- [Pose-Transformation and Radial Distance Clustering for Unsupervised Person Re-identification](https://mlsanity.com/paper/2411.04255/) (2024)
- [Evolution of ReID: From Early Methods to LLM Integration](https://mlsanity.com/paper/2506.13039/) (2025)

## Abstract (arXiv)

Human eyes can recognize person identities based on small salient regions, i.e. human saliency is distinctive and reliable in pedestrian matching across disjoint camera views. However, such valuable information is often hidden when computing similarities of pedestrian images with existing approaches. Inspired by our user study result of human perception on human saliency, we propose a novel perspective for person re-identification based on learning human saliency and matching saliency distribution. The proposed saliency learning and matching framework consists of four steps: (1) To handle misalignment caused by drastic viewpoint change and pose variations, we apply adjacency constrained patch matching to build dense correspondence between image pairs. (2) We propose two alternative methods, i.e. K-Nearest Neighbors and One-class SVM, to estimate a saliency score for each image patch, through which distinctive features stand out without using identity labels in the training procedure. (3) saliency matching is proposed based on patch matching. Matching patches with inconsistent saliency brings penalty, and images of the same identity are recognized by minimizing the saliency matching cost. (4) Furthermore, saliency matching is tightly integrated with patch matching in a unified structural RankSVM learning framework. The effectiveness of our approach is validated on the VIPeR dataset and the CUHK01 dataset. Our approach outperforms the state-of-the-art person re-identification methods on both datasets.