Skip to main content
SpringerLink
Log in

Adaptive Graph Attention Network in Person Re-Identification

  • APPLICATION PROBLEMS
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

This paper approaches a significant problem in computer vision: re-identifying a person when having groups of people. Re-identifying by group context is a new direction for improving traditional single-object re-identifying tasks by additional information from group layout and group member variations. Furthermore, adding new improvements in the graph convolution layer structure or using more powerful theories enhances the model’s accuracy. In this study, we propose to leverage the information of group objects: people and subgroups of two or three people inside a group image from the CUHK-SYSU dataset. The organization of data is based on the relational representation of the central node, and the observed nodes further incorporate their features extracted through the Resnet backbone. We also recommend using the SeLU activation function in the graph convolution model for experiments. The key challenge in implementing is to define the optimal group-wise matching using adaptive graph attention based on a graph convolution network modified and training techniques. The experiment results showed that our method improved the model’s learning efficiency by approximately 1.2% compared to the mean average precision score. Moreover, the optimal number of learning parameters is reduced to one third compared to the original.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.

Similar content being viewed by others

REFERENCES

  1. S. M. Assari, H. Idrees, and M. Shah, “Human re-identification in crowd videos using personal, social and environmental constraints,” in Computer Vision – ECCV 2016, Ed. by B. Leibe, J. Matas, N. Sebe, and M. Welling, Lecture Notes in Computer Science, vol. 9906 (Springer, Cham, 2016), pp. 119–136, 2016.  https://doi.org/10.1007/978-3-319-46475-6_8

    Book  Google Scholar 

  2. J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun, “Spectral networks and locally connected networks on graphs” (2014). arXiv:1312.6203

  3. M. Cao, C. Chen, X. Hu, and S. Peng, “From groups to co-traveler sets: Pair matching based person re-identification framework,” in IEEE Int. Conf. on Computer Vision Workshops (ICCVW), Venice, 2017 (IEEE, 2017), pp. 2573–2582.  https://doi.org/10.1109/ICCVW.2017.302

  4. D. Chen, S. Zhang, W. Ouyang, J. Yang, and Y. Tai, “Person search via a mask-guided two-stream CNN model,” in Computer Vision – ECCV 2018, Ed. by V. Ferrari, M. Hebert, C. Sminchisescu, and Y. Weiss, Lecture Notes in Computer Science, vol. 11211 (Springer, Cham, 2018), pp. 764–781.  https://doi.org/10.1007/978-3-030-01234-2_45

    Book  Google Scholar 

  5. J. Deng, W. Dong, R. Socher, L. J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in IEEE Conf. on Computer Vision and Pattern Recognition, Miami, 2009 (IEEE, 2009), pp. 248–255. https://doi.org/10.1109/CVPR.2009.5206848

  6. V. V. Devyatkov, A. N. Alfimtsev, and A. R. Taranyan, “Multicamera human re-identification based on covariance descriptor,” Pattern Recognit. Image Anal. 28, 232–242 (2018).  https://doi.org/10.1134/S1054661818020025

    Article  Google Scholar 

  7. P. N. Druzhkov and V. D. Kustikova, “A survey of deep learning methods and software tools for image classification and object detection,” Pattern Recognit. Image Anal. 26, 9–15 (2016). https://doi.org/10.1134/S1054661816010065

    Article  Google Scholar 

  8. D. K. Duvenaud, D. Maclaurin, J. Aguilera-Iparraguirre, R. Gómez-Bombarelli, T. Hirzel, A. Aspuru-Guzik, and R. P. Adams, “Convolutional networks on graphs for learning molecular fingerprints,” in Proc. 28th Int. Conf. on Neural Information Processing Systems, 2015, Ed. by C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett (MIT Press, Cambridge, Mass., 2015), vol. 2, pp. 2224–2232.

  9. C. L. Giles, K. D. Bollacker and S. Lawrence, “Citeseer: An automatic citation indexing system’” in Proc. Third ACM Conf. on Digital Libraries, Pittsburgh, Pa., 1998, Ed. by I. Witten, R. Akscyn, and F. M. Shipman (Association for Computing Machinery, New York, 1998), pp. 89–98.  https://doi.org/10.1145/276675.276685

  10. V. A. Golovko, A. A. Kroshchanka, and E. V. Mikhno, “Deep neural networks: Selected aspects of learning and application,” Pattern Recognit. Image Anal. 31, 132–143 (2021).  https://doi.org/10.1134/S1054661821010090

    Article  Google Scholar 

  11. W.L. Hamilton, Graph Representation Learning, Synthesis Lectures on Artificial Intelligence and Machine Learning, vol. 14 (3) (Morgan & Claypool, 2020).  https://doi.org/10.2200/S01045ED1V01Y202009AIM046

  12. Z. He and L. Zhang, “End-to-end detection and re-identification integrated net for person search,” in Computer Vision – ACCV 2018, Ed. by C. Jawahar, H. Li, G. Mori, and K. Schindler, Lecture Notes in Computer Science, vol. 11362 (Springer, Cham, 2019), pp. 349-364. https://doi.org/10.1007/978-3-030-20890-5_23

    Book  Google Scholar 

  13. M. Henaff, J. Bruna, and Y. LeCun, “Deep convolutional networks on graph-structured data” (2015) arXiv:1506.05163

  14. P. D. Hung and N. T. Su, “Unsafe construction behavior classification using deep convolutional neural network,” Pattern Recognit. Image Anal. 31, 271–284 (2021).  https://doi.org/10.1134/S1054661821020073

    Article  Google Scholar 

  15. G. Klambauer, T. Unterthiner, A. Mayr, and S. Hochreiter, “Self-normalizing neural networks,” in Proc. 31st Int. Conf. on Neural Information Processing Systems, Ed. by U. von Luxburg, I. Guyon, S. Bengio, H. Wallach, and R. Fergus (Curran Associates, Red Hook, N.Y., 2017), pp. 972–981.

  16. G. Lisanti, N. Martinel, A. D Bimbo, and G. L. Foresti, “Group re-identification via unsupervised transfer of sparse features encoding,” in IEEE Int. Conf. on Computer Vision (ICCV), Venice, 2017 (IEEE, 2017), pp. 2468–2477.  https://doi.org/10.1109/ICCV.2017.268

  17. H. Liu, J. Feng, Z. Jie, K. Jayashree, B. Zhao, M. Qi, J. Jiang, and S. Yan, “Neural person search machines” (2017). arXiv:1707.06777

  18. A. K. McCallum, K. Nigam, J. Rennie, and K. Seymore, “Automating the construction of internet portals with machine learning,” Inf. Retr. 3, 127–163 (2000).  https://doi.org/10.1023/A:1009953814988

    Article  Google Scholar 

  19. S. Paisitkriangkrai, C. Shen, and A. van den Hengel, “Learning to rank in person re-identification with metric ensembles,” in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 2015 (IEEE, 2015), pp. 1846–1855.  https://doi.org/10.1109/CVPR.2015.7298794

  20. A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, and A. Lerer, “Automatic differentiation in PyTorch,” in NIPS 2017 Workshop Autodiff, 2017 (2017).

  21. D. Pedamonti, “Comparison of non-linear activation functions for deep neural networks on MNIST classification task” (2018). arXiv:1804.02763

  22. V. D. B. Rianne, N. K. Thomas, and W. Max, “Graph convolutional matrix completion” (2017). arXiv:1706.02263

  23. A. Sanchez-Gonzalez, J. Godwin, T. Pfaff, R. Ying, J. Leskovec, and P. W. Battaglia, “Learning to simulate complex physics with graph networks,” Proc. Mach. Learn. Res. 119, 8459–8468 (2020).

    Google Scholar 

  24. P. Sen, G. Namata, M. Bilgic, L. Getoor, B. Galligher, and T. Eliassi-Rad, “Collective classification in network data,” AI Mag. 29, 93 (2008).  https://doi.org/10.1609/aimag.v29i3.2157

    Article  Google Scholar 

  25. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in Proceedings of the 5th International Conference on Learning Representations, 2017 (2017). arXiv:1609.02907 [cs.LG]

  26. E. W. Weisstein, “Laplacian matrix.” https://mathworld.wolfram.com/. Cited May 22, 2021.

  27. T. Xiao, S. Li, B. Wang, L. Lin, and X. Wang, “Joint detection and identification feature learning for person search,” in IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, 2017 (IEEE, 2017), pp. 3415–3424.  https://doi.org/10.1109/CVPR.2017.360

  28. J. Xiao, Y. Xie, T. Tillo, K. Huang, Y. Wei, and J. Feng, “IAN: The individual aggregation network for person search”, Pattern Recognit. 87, 332–340 (2019).  https://doi.org/10.1016/j.patcog.2018.10.028

    Article  Google Scholar 

  29. Y. Xu, B. Ma, R. Huang, and L. Lin, “Person search in a scene by jointly modeling people’s commonness and person uniqueness,” in Proc. 22nd ACM International Conference on Multimedia, Orlando, Fla., 2014 (Association for Computing Machinery, New York, 2014), pp. 937–940.  https://doi.org/10.1145/2647868.2654965

  30. Y. Yan, Q. Zhang, B. Ni, W. Zhang, M. Xu, and X. Yang, “Learning context graph for person search,” in IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), Long Beach, 2019 (IEEE, 2019), pp. 2158–2167.  https://doi.org/10.1109/CVPR.2019.00226

  31. S. Ye, R. P. Bohush, H. Chen, I. Yu. Zakharava, and S. V. Ablameyko, “Person tracking and reidentification for multicamera indoor video surveillance systems,” Pattern Recognit. Image Anal. 30, 827–837 (2020).  https://doi.org/10.1134/S1054661820040136

    Article  Google Scholar 

  32. S. Zhang and H. Yu, “Person re-identification by multi-camera networks for internet of things in smart cities,” IEEE Access 6, 76111–76117 (2018).  https://doi.org/10.1109/ACCESS.2018.2883560

    Article  Google Scholar 

  33. M. Zhu, Recall, Precision and Average Precision, Technical Report (Department of Statistics and Actuarial Science, Univ. of Waterloo, Waterloo, 2004).

Download references

ACKNOWLEDGMENTS

We would like to thank our colleagues in the Information Technology Specialization Department of FPT University, Hanoi, Vietnam for their critical and relevant comments on the manuscript; Colleagues in the English Department who have helped to polish the English text.

Author information

Authors and Affiliations

  1. FPT University, Hoa Lac High Tech Park, 10000, Hanoi, Vietnam

    L. D. Duy & P. D. Hung

Authors
  1. L. D. Duy
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. P. D. Hung
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to P. D. Hung.

Ethics declarations

COMPLIANCE WITH ETHICAL STANDARDS

This article is a completely original work of its authors; it has not been published before and will not be sent to other publications until the PRIA Editorial Board decides not to accept it for publication.

Conflict of Interest

The authors declare that they have no conflicts of interest.

Additional information

Le Dinh Duy, AI engineer graduated from FPT University, Hanoi, Vietnam. Since 2018, he has been an advisor of SAP-LAB at FPT University.

His current research interests include artificial intelligence, image processing, Internet of Things, big data.

Phan Duy Hung received his PhD degree from INP Grenoble France, in 2008. Since 2009, he has worked as a Lecturer, and served as the Head of Department and the Director of the Master Program in Software engineering at FPT University, Hanoi, Vietnam.

His current research interests include digital signal and image processing, Internet of Things, big data, artificial intelligence, measurement and control systems, and industrial networking.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Duy, L.D., Hung, P.D. Adaptive Graph Attention Network in Person Re-Identification. Pattern Recognit. Image Anal. 32, 384–392 (2022). https://doi.org/10.1134/S1054661822020080

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661822020080

Keywords:

Search

Navigation