# Dynamic Label Graph Matching for Unsupervised Video Re-Identification

arXiv: https://arxiv.org/abs/1709.09297 · HTML: https://mlsanity.com/paper/1709.09297/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2017.

## Built on by (most cited first, 23 of 23)

- [Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?](https://mlsanity.com/paper/2105.02498/) (2021)
- [Deep learning-based person re-identification methods: A survey and outlook of recent works](https://mlsanity.com/paper/2110.04764/) (2021)
- [Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identification](https://mlsanity.com/paper/2108.06493/) (2021)
- [Robust Differentiable SVD](https://mlsanity.com/paper/2104.03821/) (2021)
- [Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identification](https://mlsanity.com/paper/2301.09498/) (2023)
- [Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification](https://mlsanity.com/paper/2201.05820/) (2022)
- [Video Person Re-identification using Attribute-enhanced Features](https://mlsanity.com/paper/2108.06946/) (2021)
- [Unsupervised Person Re-Identification: A Systematic Survey of Challenges and Solutions](https://mlsanity.com/paper/2109.06057/) (2021)
- [Population-Based Evolutionary Gaming for Unsupervised Person Re-identification](https://mlsanity.com/paper/2306.05236/) (2023)
- [Unsupervised Video Person Re-identification via Noise and Hard frame Aware Clustering](https://mlsanity.com/paper/2106.05441/) (2021)
- [Unsupervised Person Re-Identification with Wireless Positioning under Weak Scene Labeling](https://mlsanity.com/paper/2110.15610/) (2021)
- [Exploiting Robust Unsupervised Video Person Re-identification](https://mlsanity.com/paper/2111.05170/) (2021)
- [Camera Alignment and Weighted Contrastive Learning for Domain Adaptation in Video Person ReID](https://mlsanity.com/paper/2211.03626/) (2022)
- [Combining human parsing with analytical feature extraction and ranking schemes for high-generalization person reidentification](https://mlsanity.com/paper/2207.14243/) (2022)
- [Self-Paced Uncertainty Estimation for One-shot Person Re-Identification](https://mlsanity.com/paper/2104.09152/) (2021)
- [PGGANet: Pose Guided Graph Attention Network for Person Re-identification](https://mlsanity.com/paper/2111.14411/) (2021)
- [Deep Probabilistic Graph Matching](https://mlsanity.com/paper/2201.01603/) (2022)
- [Generalizable Re-Identification from Videos with Cycle Association](https://mlsanity.com/paper/2211.03663/) (2022)
- [Unsupervised Noisy Tracklet Person Re-identification](https://mlsanity.com/paper/2101.06391/) (2021)
- [A Free Lunch to Person Re-identification: Learning from Automatically Generated Noisy Tracklets](https://mlsanity.com/paper/2204.00891/) (2022)
- [End-to-End Context-Aided Unicity Matching for Person Re-identification](https://mlsanity.com/paper/2210.12008/) (2022)
- [Unleashing the Potential of Tracklets for Unsupervised Video Person Re-Identification](https://mlsanity.com/paper/2406.14261/) (2024)
- [FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification](https://mlsanity.com/paper/2508.17431/) (2025)

## Abstract (arXiv)

Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models. Specifically, we propose to construct a graph for samples in each camera, and then graph matching scheme is introduced for cross-camera labeling association. While labels directly output from existing graph matching methods may be noisy and inaccurate due to significant cross-camera variations, this paper proposes a dynamic graph matching (DGM) method. DGM iteratively updates the image graph and the label estimation process by learning a better feature space with intermediate estimated labels. DGM is advantageous in two aspects: 1) the accuracy of estimated labels is improved significantly with the iterations; 2) DGM is robust to noisy initial training data. Extensive experiments conducted on three benchmarks including the large-scale MARS dataset show that DGM yields competitive performance to fully supervised baselines, and outperforms competing unsupervised learning methods.