Cross-Modal Contrastive Learning for Clothing-Invariant Person Re-Identification in Smart Surveillance Systems
Keywords:
person re-identification; cross-modal contrastive learning; clothing invariance; smart surveillance; system architecture; fairness; sustainabilityAbstract
Person re-identification in distributed camera networks forms a cornerstone of modern smart surveillance, enabling persistent tracking of individuals across disjoint views for security, forensics, and operational analytics. Yet a fundamental vulnerability undermines current systems: reliance on static appearance cues that break down when subjects change clothing. This paper addresses the clothing-invariant re-identification challenge through a cross-modal contrastive learning framework conceived not merely as an algorithmic novelty but as an entire system-level reconfiguration of sensing, representation, and deployment. We examine how multi-modal streams—visible spectrum, infrared, depth, and gait dynamics—can be aligned in a shared embedding space using contrastive objectives that enforce invariance to clothing while preserving identity-discriminative structure. The discussion is oriented around structural trade-offs in the architecture, the decoupling of feature-driven and multimodal fusion attention, and the embedding of such models within heterogeneous edge-cloud infrastructures. We analyze deployment concerns including real-time inference under resource constraints, privacy-preserving federated learning, resilience to environmental and adversarial perturbations, and fairness across demographic subgroups that may be disproportionately affected by appearance changes. Governance, algorithmic transparency, and energy sustainability are interconnected dimensions that we argue must be integrated into the design cycle of next-generation surveillance AI. By reframing clothing-invariant person re-identification as a socio-technical system problem, this paper provides a comprehensive blueprint for engineers, policymakers, and infrastructure architects striving for robust, equitable, and maintainable smart surveillance ecosystems.
References
1. Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015). Scalable person re-identification: A benchmark. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1116-1124). IEEE.
2. Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., & Hoi, S. C. H. (2021). Deep learning for person re-identification: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(6), 2872-2893.
3. Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning (pp. 1597-1607). PMLR.
4. He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9729-9738). IEEE.
5. Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., & Krishnan, D. (2020). Supervised contrastive learning. Advances in Neural Information Processing Systems, 33, 18661-18673.
6. Qian, X., Wang, W., Zhang, L., Zhu, F., Fu, Y., Xiang, T., Jiang, Y.-G., & Xue, X. (2020). Long-term cloth-changing person re-identification. In Proceedings of the Asian Conference on Computer Vision (ACCV).
7. Wu, A., Zheng, W. S., Yu, H. X., Gong, S., & Lai, J. (2017). RGB-infrared cross-modality person re-identification. In Proceedings of the IEEE International Conference on Computer Vision (pp. 5380-5389). IEEE.
8. Ananthanarayanan, G., Bahl, P., Bodík, P., Chintalapudi, K., Philipose, M., Ravindranath, L., & Sinha, S. (2017). Real-time video analytics: The killer app for edge computing. IEEE Computer, 50(10), 58-67.
9. Buolamwini, J., & Gebru, T. (2018). Gender shades: Intersectional accuracy disparities in commercial gender classification. In Conference on Fairness, Accountability and Transparency (pp. 77-91). PMLR.
10. Custers, B., Dechesne, F., Sears, A. M., Tani, T., & van der Hof, S. (2018). A comparison of data protection legislation and policies in the EU and the US. International Data Privacy Law, 8(1), 1-19.
11. Zhong, Z., Zheng, L., Luo, Z., Li, S., & Yang, Y. (2019). Invariance matters: Exemplar memory for domain adaptive person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 598-607). IEEE.
12. Ding, Y., Wang, X., Yuan, H., Qu, M., & Jian, X. (2025). Decoupling feature-driven and multimodal fusion attention for clothing-changing person re-identification. Artificial Intelligence Review, 58(8), 241.
13. Li, S., Sun, J., Li, Y., & Liu, T. (2021). Relation-aware knowledge distillation for lightweight person re-identification. IEEE Transactions on Circuits and Systems for Video Technology, 32(4), 1993-2007.
14. Wang, Z., Liu, Z., Liu, D., & Zheng, N. (2021). Gait recognition via disentangled representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 15946-15955). IEEE.
15. Zhu, J., Liao, S., Lei, Z., & Li, S. Z. (2020). Federated person re-identification. In Proceedings of the 28th ACM International Conference on Multimedia (pp. 3202-3210). ACM.
16. Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017). Efficient processing of deep neural networks: A tutorial and survey. Proceedings of the IEEE, 105(12), 2295-2329.
17. Bai, S., Li, Y., Zhou, Y., Li, Z., & Xie, Y. (2021). Adversarial metric attack and defense for person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(8), 4131-4146.
18. Torralba, A., & Efros, A. A. (2011). Unbiased look at dataset bias. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1521-1528). IEEE.
19. He, S., Luo, H., Wang, P., Wang, F., Li, H., & Jiang, W. (2021). Transreid: Transformer-based object re-identification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 15013-15022). IEEE.
20. Dhar, P. (2020). The carbon impact of artificial intelligence. Nature Machine Intelligence, 2(8), 423-425.
21. Sreenu, G., & Saleem Durai, M. A. (2019). Intelligent video surveillance: A review through deep learning techniques for crowd analysis. Journal of Big Data, 6(1), 1-27.
22. Rahman, M. A., Hossain, M. S., & Loukas, G. (2020). A blockchain-based framework for secure data sharing in smart surveillance. IEEE Access, 8, 103146-103157.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Artificial Intelligence Engineering and Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
