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.
Similar content being viewed by others
REFERENCES
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
J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun, “Spectral networks and locally connected networks on graphs” (2014). arXiv:1312.6203
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
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
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
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
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
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.
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
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
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
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
M. Henaff, J. Bruna, and Y. LeCun, “Deep convolutional networks on graph-structured data” (2015) arXiv:1506.05163
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
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.
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
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
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
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
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).
D. Pedamonti, “Comparison of non-linear activation functions for deep neural networks on MNIST classification task” (2018). arXiv:1804.02763
V. D. B. Rianne, N. K. Thomas, and W. Max, “Graph convolutional matrix completion” (2017). arXiv:1706.02263
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).
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
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]
E. W. Weisstein, “Laplacian matrix.” https://mathworld.wolfram.com/. Cited May 22, 2021.
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
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
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
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
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
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
M. Zhu, Recall, Precision and Average Precision, Technical Report (Department of Statistics and Actuarial Science, Univ. of Waterloo, Waterloo, 2004).
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
Corresponding author
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
About this article
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
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661822020080