Home

Awesome

Dynamic Label Graph Matching for Unsupervised Video Re-Identification

Demo code for Dynamic Label Graph Matching for Unsupervised Video Re-Identification in ICCV 2017.

We revised the evaluation protocol for the IDE on MARS dataset. In previous version, due to file traverse problem, which leads a different evaluation protocol, we achieve an extremely high performance (Unsupervised rank-1 65.2%, and supervised 75.8%) compared with other baselines in our cv-foundation version. We re-evaluate our perfomance under standard settings, the rank-1 is 36.8% for our unsupervised method, and the supervised upper bound is 56.2%. Please refer to the version on our website and github for latest results. PDF

1. Test on PRID-2011 and iLIDS-VID datasets.

Results

DatasetsRank@1Rank@5Rank@10
#PRID-201173.1%92.5%96.7%
#iLIDS-VID37.1%61.3%72.2%

Results

MethodsRank@1Rank@5mAP
#LOMO24.6%42.6%11.8%
#IDE36.8%54.0%21.3%

Citation

Please cite this paper in your publications if it helps your research:

@inproceedings{iccv17dgm,
  title={Dynamic Label Graph Matching for Unsupervised Video Re-Identification},
  author={Ye, Mang and Ma, Andy J and Zheng, Liang and Li, Jiawei and Yuen, Pong C.},
  booktitle={ICCV},
  year={2017},
}

Contact: mangye@comp.hkbu.edu.hk