More Web Proxy on the site http://driver.im/

research-article

Tensor Multi-Task Learning for Person Re-Identification

Authors:

Zhizhong Zhang,

Wensheng Zhang,

Yongqiang Tang,

Qi TianAuthors Info & Claims

IEEE Transactions on Image Processing, Volume 29

Pages 2463 - 2477

https://doi.org/10.1109/TIP.2019.2949929

Published: 01 January 2020 Publication History

Abstract

This article presents a tensor multi-task model for person re-identification (Re-ID). Due to discrepancy among cameras, our approach regards Re-ID from multiple cameras as different but related classification tasks, each task corresponding to a specific camera. In each task, we distinguish the person identity as a one-vs-all linear classification problem, where one classifier is associated with a specific person. By constructing all classifiers into a task-specific projection matrix, the proposed method could utilize all the matrices to form a tensor structure, and jointly train all the tasks in a uniform tensor space. In this space, by assuming the features of the same person under different cameras are generated from a latent subspace, and different identities under the same perspective share similar patterns, the high-order correlations, not only across different tasks but also within a certain task, can be captured by utilizing a new type of low-rank tensor constraint. Therefore, the learned classifiers transform the original feature vector into the latent space, where feature distributions across cameras can be well-aligned. Moreover, this model can be incorporated into multiple visual features to boost the performance, and easily extended to the unsupervised setting. Extensive experiments and comparisons with recent Re-ID methods manifest the competitive performance of our method.

References

[1]

W. Chen, X. Chen, J. Zhang, and K. Huang, “A multi-task deep network for person re-identification,” in Proc. AAAI, 2017, pp. 1–7.

[2]

M. Li, F. Shen, J. Wang, C. Guan, and J. Tang, “Person re-identification with activity prediction based on hierarchical spatial-temporal model,” Neurocomputing, vol. 275, pp. 1200–1207, Jan. 2017.

[3]

H. Yao, S. Zhang, Y. Zhang, J. Li, and Q. Tian, “Deep representation learning with part loss for person re-identification,” 2017, arXiv:1707.00798. [Online]. Available: https://arxiv.org/abs/1707.00798

[4]

S. Liao, Y. Hu, X. Zhu, and S. Z. Li, “Person re-identification by local maximal occurrence representation and metric learning,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015, pp. 2197–2206.

[5]

Y.-C. Chen, X. Zhu, W.-S. Zheng, and J.-H. Lai, “Person re-identification by camera correlation aware feature augmentation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no., pp. 392–408, Feb. 2018.

Digital Library

[6]

P. Penget al., “Unsupervised cross-dataset transfer learning for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 1306–1315.

[7]

T. Matsukawa, T. Okabe, E. Suzuki, and Y. Sato, “Hierarchical Gaussian descriptor for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 1363–1372.

[8]

Z. Zhang, Y. Xie, W. Zhang, and Q. Tian, “Effective image retrieval via multilinear multi-index fusion,” 2017, arXiv:1709.09304. [Online]. Available: https://arxiv.org/abs/1709.09304

[9]

D. Chen, Z. Yuan, B. Chen, and N. Zheng, “Similarity learning with spatial constraints for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 1268–1277.

[10]

C. Su, S. Zhang, J. Xing, W. Gao, and Q. Tian, “Deep attributes driven multi-camera person re-identification,” in Proc. Eur. Conf. Comput. Vis., 2016, pp. 475–491.

[11]

H. Fan, L. Zheng, and Y. Yang, “Unsupervised person re-identification: Clustering and fine-tuning,” 2017, arXiv:1705.10444. [Online]. Available: https://arxiv.org/abs/1705.10444

[12]

H. Liu, J. Feng, M. Qi, J. Jiang, and S. Yan, “End-to-end comparative attention networks for person re-identification,” IEEE Trans. Image Process., vol. 26, no. 7, pp. 3492–3506, Jul. 2017.

Digital Library

[13]

L. Ma, X. Yang, and D. Tao, “Person re-identification over camera networks using multi-task distance metric learning,” IEEE Trans. Image Process., vol. 23, no. 8, pp. 3656–3670, Aug. 2014.

[14]

Y. Sun, L. Zheng, W. Deng, and S. Wang, “SVDNet for pedestrian retrieval,” in Proc. IEEE Int. Conf. Comput. Vis., Oct. 2017, pp. 3800–3808.

[15]

Z. Zhong, L. Zheng, D. Cao, and S. Li, “Re-ranking person re-identification with k-reciprocal encoding,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jul. 2017, pp. 1318–1327.

[16]

L. Zhang, T. Xiang, and S. Gong, “Learning a discriminative null space for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 1239–1248.

[17]

R. R. Varior, B. Shuai, J. Lu, D. Xu, and G. Wang, “A siamese long short-term memory architecture for human re-identification,” in Proc. Eur. Conf. Comput. Vis., 2016, pp. 135–153.

[18]

R. R. Varior, M. Haloi, and G. Wang, “Gated siamese convolutional neural network architecture for human re-identification,” in Proc. Eur. Conf. Comput. Vis., 2016, pp. 791–808.

[19]

L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian, “Scalable person re-identification: A benchmark,” in Proc. IEEE Int. Conf. Comput. Vis., Dec. 2015, pp. 1116–1124.

[20]

Y. Jiaet al., “Caffe: Convolutional architecture for fast feature embedding,” in Proc. ACM Int. Conf. Multimedia, 2014, pp. 675–678.

[21]

Y. Xie, D. Tao, W. Zhang, and L. Zhang, “Multi-view subspace clustering via relaxed $L_{1}$ -norm of tensor multi-rank,” 2016, arXiv:1610.07126v1. [Online]. Available: https://arxiv.org/abs/1610.07126v1

[22]

Z. Zhang, G. Ely, S. Aeron, N. Hao, and M. Kilmer, “Novel methods for multilinear data completion and de-noising based on tensor-SVD,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2014, pp. 3842–3849.

[23]

Z. Lin, M. Chen, and Y. Ma, “The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices,” UIUC, Champaign, IL, USA, Tech. Rep. UILUENG-09-2215, 2009.

[24]

O. Semerci, N. Hao, M. E. Kilmer, and E. L. Miller, “Tensor-based formulation and nuclear norm regularization for multienergy computed tomography,” IEEE Trans. Image Process., vol. 23, no. 4, pp. 1678–1693, Apr. 2014.

Digital Library

[25]

J. Valmadre, L. Bertinetto, J. Henriques, A. Vedaldi, and P. H. S. Torr, “End-to-end representation learning for correlation filter based tracking,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jul. 2017, pp. 2805–2813.

[26]

A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Proc. Adv. Neural Inf. Process. Syst., 2012, pp. 1097–1105.

[27]

X. Zhao, N. Wang, Y. Zhang, S. Du, Y. Gao, and J. Sun, “Beyond pairwise matching: Person reidentification via high-order relevance learning,” IEEE Trans. Neural Netw. Learn. Syst., vol. 29, no. 8, pp. 3701–3714, Aug. 2018. 10.1109/TNNLS.2017.2736640.

[28]

H.-X. Yu, A. Wu, and W.-S. Zheng, “Cross-view asymmetric metric learning for unsupervised person re-identification,” in Proc. IEEE Int. Conf. Comput. Vis., Oct. 2017, pp. 994–1002.

[29]

S. Paisitkriangkrai, C. Shen, and A. van den Hengel, “Learning to rank in person re-identification with metric ensembles,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2015, pp. 1846–1855.

[30]

M. Geng, Y. Wang, T. Xiang, and Y. Tian, “Deep transfer learning for person re-identification,” 2016, arXiv:1611.05244. [Online]. Available: https://arxiv.org/abs/1611.05244

[31]

M. Köstinger, M. Hirzer, P. Wohlhart, P. M. Roth, and H. Bischof, “Large scale metric learning from equivalence constraints,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2012, pp. 2288–2295.

[32]

Y.-C. Chen, W.-S. Zheng, J.-H. Lai, and P. C. Yuen, “An asymmetric distance model for cross-view feature mapping in person reidentification,” IEEE Trans. Circuits Syst. Video Technol., vol. 27, no. 8, pp. 1661–1675, Aug. 2017.

Digital Library

[33]

D. Gary, S. Brennan, and H. Tao, “Evaluating appearance models for recognition, reacquisition, and tracking,” in Proc. IEEE Int. Workshop Perform. Eval. Tracking Surveill., 2007, pp. 1–7.

[34]

W. Li, R. Zhao, and X. Wang, “Human reidentification with transferred metric learning,” in Proc. Asian Conf. Comput. Vis., 2012, pp. 31–44.

[35]

W. Li, R. Zhao, T. Xiao, and X. Wang, “DeepReID: Deep filter pairing neural network for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2014, pp. 152–159.

[36]

S. Bak and P. Carr, “One-shot metric learning for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jul. 2017, pp. 2990–2999.

[37]

E. Kodirov, T. Xiang, Z. Fu, and S. Gong, “Person re-identification by unsupervised $\ell_{1}$ graph learning,” in Proc. Eur. Conf. Comput. Vis., 2016, pp. 178–195.

[38]

G. Lisanti, N. Martinel, A. D. Bimbo, and G. L. Foresti, “Group re-identification via unsupervised transfer of sparse features encoding,” in Proc. IEEE Int. Conf. Comput. Vis., Oct. 2017, pp. 2449–2458.

[39]

T. Xiao, H. Li, W. Ouyang, and X. Wang, “Learning deep feature representations with domain guided dropout for person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 1249–1258.

[40]

A. Hermans, L. Beyer, and B. Leibe, “In defense of the triplet loss for person re-identification,” 2017, arXiv:1703.07737. [Online]. Available: https://arxiv.org/abs/1703.07737

[41]

D. Cheng, X. Chang, L. Liu, A. G. Hauptmann, Y. Gong, and N. Zheng, “Discriminative dictionary learning with ranking metric embedded for person re-identification,” in Proc. Int. Joint Conf. Artif. Intell., 2017, pp. 964–970.

[42]

A. Wu, W.-S. Zheng, and J.-H. Lai, “Robust depth-based person re-identification,” IEEE Trans. Image Process., vol. 26, no. 6, pp. 2588–2603, Jun. 2017.

Digital Library

[43]

S. Bai, X. Bai, and Q. Tian, “Scalable person re-identification on supervised smoothed manifold,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jul. 2017, pp. 2530–2539.

[44]

C. Su, F. Yang, S. Zhang, Q. Tian, L. S. Davis, and W. Gao, “Multi-task learning with low rank attribute embedding for person re-identification,” in Proc. IEEE Int. Conf. Comput. Vis., Dec. 2015, pp. 3739–3747.

[45]

F. Xiong, M. Gou, O. Camps, and M. Sznaier, “Person re-identification using kernel-based metric learning methods,” in Proc. Eur. Conf. Comput. Vis., 2014, pp. 1–16.

[46]

F. Jurie and A. A. Mignon, “PCCA: New approach for distance learning from sparse pairwise constraints,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2012, pp. 2666–2672.

[47]

M. E. Kilmer, K. Braman, N. Hao, and R. C. Hoover, “Third-order tensors as operators on matrices: A theoretical and computational framework with applications in imaging,” SIAM J. Matrix Anal. Appl., vol. 34, no. 1, pp. 148–172, 2013.

Digital Library

[48]

Z. Lin, R. Liu, and Z. Su, “Linearized alternating direction method with adaptive penalty for low-rank representation,” in Proc. Adv. Neural Inf. Process. Syst., 2011, pp. 612–620.

[49]

S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein, “Distributed optimization and statistical learning via the alternating direction method of multipliers,” Found. Trends Mach. Learn., vol. 3, no. 1, pp. 1–122, Jan. 2011.

Digital Library

[50]

L. Zheng, Y. Yang, and A. G. Hauptmann, “Person re-identification: Past, present and future,” 2016, arXiv:1610.02984. [Online]. Available: https://arxiv.org/abs/1610.02984

[51]

Z. Wu, Y. Xiong, S. X. Yu, and D. Lin, “Unsupervised feature learning via non-parametric instance discrimination,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 3733–3742.

[52]

Z. Zhong, L. Zheng, Z. Luo, S. Li, and Y. Yang, “Invariance matters: Exemplar memory for domain adaptive person re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2019, pp. 598–607.

Cited By

Chen YWang SZhao YChen C(2024)Double Discrete Cosine Transform-Oriented Multi-View Subspace ClusteringIEEE Transactions on Image Processing10.1109/TIP.2024.337847133(2491-2501)Online publication date: 22-Mar-2024
https://dl.acm.org/doi/10.1109/TIP.2024.3378471
Chen ZZhang ZTan XQu YXie YEl Saddik AMei TCucchiara RBertini MTobon Vallejo DAtrey PHossain M(2023)Unveiling the Power of CLIP in Unsupervised Visible-Infrared Person Re-IdentificationProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3612050(3667-3675)Online publication date: 26-Oct-2023
https://dl.acm.org/doi/10.1145/3581783.3612050
Wang YJiang KLu HXu ZLi GChen CGeng X(2022)Encoder-decoder assisted image generation for person re-identificationMultimedia Tools and Applications10.1007/s11042-022-11907-281:7(10373-10390)Online publication date: 1-Mar-2022
https://dl.acm.org/doi/10.1007/s11042-022-11907-2
Show More Cited By

Index Terms

Tensor Multi-Task Learning for Person Re-Identification
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
      2. Computer vision tasks
  2. Machine learning
    1. Learning paradigms

Index terms have been assigned to the content through auto-classification.

Recommendations

Multi-Task Learning via Generalized Tensor Trace Norm
KDD '21: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining

The trace norm is widely used in multi-task learning as it can discover low-rank structures among tasks in terms of model parameters. Nowadays, with the emerging of big complex datasets and the popularity of deep learning techniques, tensor trace norms ...
Visual tracking via adaptive multi-task feature learning with calibration and identification

Recently multi-task feature learning has become a widely applied approach for visual tracking, since it is benefited from the shared features across tasks. However, selecting features appropriately from multiple tasks is still a challenging problem due ...
Learning sparse task relations in multi-task learning
AAAI'17: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence

In multi-task learning, when the number of tasks is large, pair-wise task relations exhibit sparse patterns since usually a task cannot be helpful to all of the other tasks and moreover, sparse task relations can reduce the risk of overfitting compared ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image IEEE Transactions on Image Processing

IEEE Transactions on Image Processing Volume 29, Issue

2020

3918 pages

ISSN:1057-7149

Issue’s Table of Contents

1057-7149 © 2019 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.

Publisher

IEEE Press

Publication History

Published: 01 January 2020

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
0
Total Downloads

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

Reflects downloads up to 15 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Chen YWang SZhao YChen C(2024)Double Discrete Cosine Transform-Oriented Multi-View Subspace ClusteringIEEE Transactions on Image Processing10.1109/TIP.2024.337847133(2491-2501)Online publication date: 22-Mar-2024
https://dl.acm.org/doi/10.1109/TIP.2024.3378471
Chen ZZhang ZTan XQu YXie YEl Saddik AMei TCucchiara RBertini MTobon Vallejo DAtrey PHossain M(2023)Unveiling the Power of CLIP in Unsupervised Visible-Infrared Person Re-IdentificationProceedings of the 31st ACM International Conference on Multimedia10.1145/3581783.3612050(3667-3675)Online publication date: 26-Oct-2023
https://dl.acm.org/doi/10.1145/3581783.3612050
Wang YJiang KLu HXu ZLi GChen CGeng X(2022)Encoder-decoder assisted image generation for person re-identificationMultimedia Tools and Applications10.1007/s11042-022-11907-281:7(10373-10390)Online publication date: 1-Mar-2022
https://dl.acm.org/doi/10.1007/s11042-022-11907-2
Wang JZhang ZChen MZhang YWang CSheng BQu YXie Y(2022)Optimal Transport for Label-Efficient Visible-Infrared Person Re-IdentificationComputer Vision – ECCV 202210.1007/978-3-031-20053-3_6(93-109)Online publication date: 23-Oct-2022
https://dl.acm.org/doi/10.1007/978-3-031-20053-3_6
Zhou CGui SZhang GZhang QWang XWei J(2021)Social Group Behavior Analysis Model Integrating Multitask Learning and Convolutional Neural NetworkWireless Communications & Mobile Computing10.1155/2021/55402012021Online publication date: 1-Jan-2021
https://dl.acm.org/doi/10.1155/2021/5540201
Wang KWang PDing CTao D(2021)Batch Coherence-Driven Network for Part-Aware Person Re-IdentificationIEEE Transactions on Image Processing10.1109/TIP.2021.306090930(3405-3418)Online publication date: 8-Mar-2021
https://dl.acm.org/doi/10.1109/TIP.2021.3060909

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents