Dynamic Label Graph Matching for Unsupervised Video Re-identification

@article{Ye2017DynamicLG,
  title={Dynamic Label Graph Matching for Unsupervised Video Re-identification},
  author={Mang Ye and Andy Jinhua Ma and Liang Zheng and Jiawei Li and Pong C. Yuen},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={5152-5160}
}
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… CONTINUE READING
Highly Cited
This paper has 41 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 9 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 26 extracted citations

Joint Discriminative Learning of Deep Dynamic Textures for 3D Mask Face Anti-Spoofing

IEEE Transactions on Information Forensics and Security • 2019
View 1 Excerpt

Feature Matching Based on Top K Rank Similarity

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 1 Excerpt

References

Publications referenced by this paper.
Showing 1-10 of 43 references

Efficient PSD Constrained Asymmetric Metric Learning for Person Re-Identification

2015 IEEE International Conference on Computer Vision (ICCV) • 2015
View 9 Excerpts
Highly Influenced

Person re-identification by Local Maximal Occurrence representation and metric learning

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 9 Excerpts
Highly Influenced

Joint Probabilistic Matching Using m-Best Solutions

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016
View 3 Excerpts
Highly Influenced

Multi-Graph Matching via Affinity Optimization with Graduated Consistency Regularization

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2016
View 4 Excerpts
Highly Influenced

Top-Push Video-Based Person Re-identification

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016
View 6 Excerpts
Highly Influenced

and a

P. Peng, T. Xiang, Y. Wang
et. Unsupervised crossdataset transfer learning for person re-identification. In CVPR • 2016
View 5 Excerpts
Highly Influenced

A Spatio-Temporal Appearance Representation for Video-Based Pedestrian Re-Identification

2015 IEEE International Conference on Computer Vision (ICCV) • 2015
View 4 Excerpts
Highly Influenced

Joint Probabilistic Data Association Revisited

2015 IEEE International Conference on Computer Vision (ICCV) • 2015
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…