Article

Discriminative dictionary learning with ranking metric embedded for person re-identification

Authors:

Alexander G. Hauptmann,

Nanning ZhengAuthors Info & Claims

IJCAI'17: Proceedings of the 26th International Joint Conference on Artificial Intelligence

Pages 964 - 970

Published: 19 August 2017 Publication History

Abstract

The goal of person re-identification (Re-Id) is to match pedestrians captured from multiple non-overlapping cameras. In this paper, we propose a novel dictionary learning based method with ranking metric embedded, for person Re-Id. A new and essential ranking graph Laplacian term is introduced, which minimizes the intra-personal compactness and maximizes the inter-personal dispersion in the objective. Different from the traditional dictionary learning based approaches and their extensions, which just use the same or not information, our proposed method can explore the ranking relationship among the person images, which is essential for such retrieval related tasks. Simultaneously, one distance measurement matrix has been explicitly learned in the model to further improve the performance. Since we have reformulated these ranking constraints into the graph Laplacian form, the proposed method is easy-to-implement but effective. We conduct extensive experiments on three widely used person Re-Id benchmark datasets, and achieve state-of-the-art performances.

References

[1]

Ejaz Ahmed, Michael Jones, and Tim K Marks. An improved deep learning architecture for person reidentification. In CVPR , pages 3908-3916, 2015.

[2]

Davide Baltieri, Roberto Vezzani, and Rita Cucchiara. 3dpes: 3d people dataset for surveillance and forensics. In Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding , pages 59-64. ACM, 2011.

Digital Library

[3]

Ying-Cong Chen, Wei-Shi Zheng, and Jianhuang Lai. Mirror representation for modeling view-specific transform in person re-identification. In IJCAI , 2015.

Digital Library

[4]

Dapeng Chen, Zejian Yuan, Badong Chen, and Nanning Zheng. Similarity learning with spatial constraints for person re-identification. In CVPR , pages 1268-1277, 2016.

[5]

Shi-Zhe Chen, Chun-Chao Guo, and Jian-Huang Lai. Deep ranking for person re-identification via joint representation learning. IEEE TIP , 2016.

[6]

De Cheng, Yihong Gong, Sanping Zhou, Jinjun Wang, and Nanning Zheng. Person re-identification by multichannel parts-based cnn with improved triplet loss function. In CVPR , pages 1335-1344, 2016.

[7]

Douglas Gray, Shane Brennan, and Hai Tao. Evaluating appearance models for recognition, reacquisition, and tracking. In ECCV , 2007.

[8]

Kaiming He, Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In CVPR , 2016.

[9]

Zhuolin Jiang, Zhe Lin, and Larry S Davis. Label consistent k-svd: Learning a discriminative dictionary for recognition. IEEE TPAMI , 35(11):2651-2664, 2013.

Digital Library

[10]

Cijo Jose and Franois Fleuret. Scalable metric learning via weighted approximate rank component analysis. In ECCV , pages 875-890, 2016.

[11]

Srikrishna Karanam, Yang Li, and Richard J Radke. Person re-identification with discriminatively trained viewpoint invariant dictionaries. In ICCV , 2015.

Digital Library

[12]

Elyor Kodirov, Tao Xiang, Zhenyong Fu, and Shaogang Gong. Person re-identification by unsupervised\ ell_1 graph learning. In ECCV , pages 178-195, 2016.

[13]

Martin Koestinger, Martin Hirzer, Paul Wohlhart, Peter M Roth, and Horst Bischof. Large scale metric learning from equivalence constraints. In CVPR , 2012.

[14]

Honglak Lee, Alexis Battle, Rajat Raina, and Andrew Y Ng. Efficient sparse coding algorithms. NIPS , 2007.

[15]

Wei Li, Rui Zhao, Tong Xiao, and Xiaogang Wang. Deepreid: Deep filter pairing neural network for person reidentification. In CVPR , pages 152-159, 2014.

Digital Library

[16]

Shengcai Liao, Yang Hu, Xiangyu Zhu, and Stan Z Li. Person re-identification by local maximal occurrence representation and metric learning. In CVPR , 2015.

[17]

Giuseppe Lisanti, Iacopo Masi, and Alberto Del Bimbo. Matching people across camera views using kernel canonical correlation analysis. In ICDSC , page 10, 2014.

Digital Library

[18]

Tetsu Matsukawa, Takahiro Okabe, Einoshin Suzuki, and Yoichi Sato. Hierarchical gaussian descriptor for person re-identification. In CVPR , 2016.

[19]

Alexis Mignon and Frédéric Jurie. Pcca: A new approach for distance learning from sparse pairwise constraints. In CVPR , pages 2666-2672, 2012.

Digital Library

[20]

Sakrapee Paisitkriangkrai, Chunhua Shen, and Anton van den Hengel. Learning to rank in person re-identification with metric ensembles. In CVPR , 2015.

[21]

Sateesh Pedagadi, James Orwell, Sergio Velastin, and Boghos Boghossian. Local fisher discriminant analysis for pedestrian re-identification. In CVPR , 2013.

Digital Library

[22]

Peixi Peng, Tao Xiang, Yaowei Wang, Massimiliano Pontil, Shaogang Gong, Tiejun Huang, and Yonghong Tian. Unsupervised cross-dataset transfer learning for person reidentification. In CVPR , pages 1306-1315, 2016.

[23]

Raphael Prates, Felipe, and William Robson Schwartz. Appearance-based person re-identification by intra-camera discriminative models and rank aggregation. In Biometrics (ICB), 2015 International Conference on , pages 65-72.

[24]

Raphael Prates, Marina Oliveira, and William Robson Schwartz. Kernel partial least squares for person re-identification. In AVSS , 2016.

[25]

Weiwei Shi, Yihong Gong, and Jinjun. Improving cnn performance with min-max objective. In IJCAI , 2016.

Digital Library

[26]

Rahul Rama Varior, Mrinal Haloi, and Gang Wang. Gated siamese convolutional neural network architecture for human re-identification. In ECCV , pages 791-808, 2016.

[27]

Rahul Rama Varior, Bing Shuai, Jiwen Lu, Dong Xu, and Gang Wang. A siamese long short-term memory architecture for human re-identification. In ECCV , 2016.

[28]

Faqiang Wang, Wangmeng Zuo, Liang Lin, David Zhang, and Lei Zhang. Joint learning of single-image and cross-image representations for person re-identification. In CVPR , pages 1288-1296, 2016.

[29]

Kilian QWeinberger and Lawrence K Saul. Distance metric learning for large margin nearest neighbor classification. JMLR , 10(Feb):207-244, 2009.

Digital Library

[30]

Lin Wu, Chunhua Shen, and Anton van den Hengel. Deep linear discriminant analysis on fisher networks: A hybrid architecture for person re-identification. Pattern Recognition , 2016.

Digital Library

[31]

Shangxuan Wu, Ying-Cong Chen, Xiang Li, Jin-Jie You, and Wei-Shi Zheng. An enhanced deep feature representation for person re-identification. In WACV , 2016.

[32]

Tong Xiao, Hongsheng Li, Wanli Ouyang, and Xiaogang Wang. Learning deep feature representations with domain guided dropout for person re-identification. CVPR , 2016.

[33]

Fei Xiong, Mengran Gou, Octavia Camps, and Mario Sznaier. Person re-identification using kernel-based metric learning methods. In ECCV , pages 1-16, 2014.

[34]

Yang Yang, Zhen Lei, Shifeng Zhang, Hailin Shi, and Stan Z Li. Metric embedded discriminative vocabulary learning for high-level person representation. In AAAI , 2016.

Digital Library

[35]

Qiang Zhang and Baoxin Li. Discriminative k-svd for dictionary learning in face recognition. In CVPR , 2010.

[36]

Li Zhang, Tao Xiang, and Shaogang Gong. Learning a discriminative null space for person re-identification. In CVPR , pages 1239-1248, 2016.

[37]

Ying Zhang, Baohua Li, Huchuan Lu, Atshushi Irie, and Xiang Ruan. Sample-specific svm learning for person re-identification. In CVPR , pages 1278-1287, 2016.

[38]

Rui Zhao, Wanli Ouyang, and Xiaogang Wang. Unsupervised salience learning for person re-identification. In CVPR , 2013.

Digital Library

Cited By

Lou XWu THu HChen D(2023)Self-Supervised Consistency Based on Joint Learning for Unsupervised Person Re-identificationACM Transactions on Multimedia Computing, Communications, and Applications10.1145/361292620:1(1-20)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.1145/3612926
Cheng DGong YShi WZhang S(2018)Person re-identification by the asymmetric triplet and identification loss functionMultimedia Tools and Applications10.1007/s11042-017-5182-z77:3(3533-3550)Online publication date: 1-Feb-2018
https://dl.acm.org/doi/10.1007/s11042-017-5182-z

Recommendations

Multiple Kernel Fisher Discriminant Metric Learning for Person Re-identification
ICVGIP '18: Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing

Person re-identification addresses the problem of matching pedestrian images across disjoint camera views. Design of feature descriptor and distance metric learning are the two fundamental tasks in person re-identification. In this paper, we propose a ...
Learning hybrid ranking representation for person re-identification
Highlights
- We propose to jointly learn ranking context cues and appearance features to exploit discriminative feature representations for person re-id.
Abstract
Contemporary person re-identification (re-id) methods mostly compute independentlya feature representation of each person image in the query set and the gallery set. This strategy fails to consider any ranking context information of ...
Joint dictionary and metric learning for person re-identification

A joint dictionary learning and metric learning algorithm is proposed.Closed-form solutions are proposed for updating the dictionary and coefficients.Hard negative weighting is utilized to alleviate amount bias.Cross datasets results validate the ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

IJCAI'17: Proceedings of the 26th International Joint Conference on Artificial Intelligence

August 2017

5253 pages

ISBN:9780999241103

Editor:
Carles Sierra
IIIA-CSIC

Sponsors

Australian Comp Soc: Australian Computer Society
NSF: National Science Foundation
Griffith University
University of Technology Sydney
AI Journal: AI Journal

Publisher

AAAI Press

Publication History

Published: 19 August 2017

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 31 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Lou XWu THu HChen D(2023)Self-Supervised Consistency Based on Joint Learning for Unsupervised Person Re-identificationACM Transactions on Multimedia Computing, Communications, and Applications10.1145/361292620:1(1-20)Online publication date: 19-Aug-2023
https://dl.acm.org/doi/10.1145/3612926
Cheng DGong YShi WZhang S(2018)Person re-identification by the asymmetric triplet and identification loss functionMultimedia Tools and Applications10.1007/s11042-017-5182-z77:3(3533-3550)Online publication date: 1-Feb-2018
https://dl.acm.org/doi/10.1007/s11042-017-5182-z

View Options

View options

Figures

Tables

Media

View Table of Conten