人員重新識別 (Re-ID) 需要一種能夠跨不同攝像機視圖識別同一個人或匹配圖庫圖像中的查詢圖像的方法，由於其廣泛的應用而受到越來越多的關注。 然而，除了光照、姿勢、視點、背景等自然困難之外，
遮擋和類似的屬性，這項任務更具挑戰性，特別是在難以獲得用於學習模型的地面實況數據的特定領域。
本論文通過提出來解決這些問題； 首先，基於字典學習的Re-ID，使用樹結構表示將注意力從全局特徵編碼到局部特徵。 此外，我們引入了簡單的新方法基於多色關聯 (MCA) 的度量來提高 Re-ID 任務的性能。 此外，我們還在群體行為識別系統中實現了這種豐富的表示作為匹配模塊，以查找人的軌跡或找到循環神經網絡 (RNN) 組件的最接近的先前真實隱藏狀態。
其次，我們提出了使用數據增強——複製圖像隨機擦除 (RIRE) 和學習合成人員 ID 來克服廣義人員 Re-ID 度量學習中的採樣問題的方法。 它在多域（可見）數據集上進行訓練
並在另一個（看不見的）數據集中進行測試。 此外，為了促進域泛化 (DG) 挑戰，我們提出了一個新的數據集，用於運行僅包含畫廊或目標圖像的馬拉松賽事。

Person Re-Identification (Re-ID) which requires a method that is able to recognize
the same person across different camera views or match the query image in the gallery
images, is getting more attention due to its broad-wide applications. However, besides
the nature difficulties such as large variety of illumination, pose, viewpoint, background,
occlusion, and similar attributes, this task is more challenging, especially in a specific
domain that difficult to obtain the ground truth data for learning the model.
This thesis contributes to the problems by proposing; first, person Re-ID based on
Dictionary learning with tree-structured representation to encode the attention from global
to local features. Moreover, we introduce simple novel method Multi-Color Association
(MCA) based metric to boost the performance of the Re-ID task. Furthermore, we also
implemented those kind of rich representation in the group behavior recognition system
as a matching module to find person trajectories or find the closest previous true hidden
states of Recurrent Neural Network (RNN) component.
Second, we propose approaches to overcome the sampling issue in the metric learning for generalized person Re-ID using data augmentation - Replicate image random erasing (RIRE) and learning synthetic person ids. It trains on multi-domain (seen) datasets
and tests in another (unseen) dataset. Moreover, to facilitate the domain generalization
(DG) challenge, we propose a new dataset in running marathon events containing only
gallery or target images.

[1] E. Ahmed, M. Jones, and T. K. Marks, “An improved deep learning architecture for person re-
identification,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3908–3916.
[2] M. R. Amer, P. Lei, and S. Todorovic, “Hirf: Hierarchical random field for collective activity recognition in videos,” in European Conference on Computer Vision. Springer, 2014, pp. 572–585.
[3] T. Bagautdinov, A. Alahi, F. Fleuret, P. Fua, and S. Savarese, “Social scene understanding: End-to-end multi-person action localization and collective activity recognition,” arXiv preprint arXiv:1611.09078, 2016.
[4] A. Bedagkar-Gala and S. K. Shah, “A survey of approaches and trends in person re-identification,”Image and Vision Computing, vol. 32, no. 4, pp. 270–286, 2014.
[5] C. M. Bishop, Pattern Recognition and Machine Learning. Springer, 2006.
[6] X. Chang, T. M. Hospedales, and T. Xiang, “Multi-level factorisation net for person re-identification," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 2109–2118.
[7] B. Chen, W. Deng, and J. Hu, “Mixed high-order attention network for person re-identification,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 371–381.
[8] G. Chen, C. Lin, L. Ren, J. Lu, and J. Zhou, “Self-critical attention learning for person re-
identification,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 9637–9646.
[9] G. Chen, Y. Lu, J. Lu, and J. Zhou, “Deep credible metric learning for unsupervised domain adaptation person re-identification,” in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VIII 16. Springer, 2020, pp. 643–659.
[10] W. Chen, X. Chen, J. Zhang, and K. Huang, “Beyond triplet loss: a deep quadruplet network for person re-identification,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 403–412.
[11] Chen Change Loy, T. Xiang, and S. Gong, “Multi-camera activity correlation analysis,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 1988–1995.
[12] W. Choi and S. Savarese, “Understanding collective activitiesof people from videos,” IEEE transactions on pattern analysis and machine intelligence, vol. 36, no. 6, pp. 1242–1257, 2014.
[13] W. Choi, K. Shahid, and S. Savarese, “What are they doing?: Collective activity classification using spatio-temporal relationship among people,” in Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on. IEEE, 2009, pp. 1282–1289.
[14] ——, “Learning context for collective activity recognition,” in Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011, pp. 3273–3280.
[15] J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, “Empirical evaluation of gated recurrent neural networks on sequence modeling,” arXiv preprint arXiv:1412.3555, 2014.
[16] A. Coates and A. Y. Ng, “Learning feature representations with k-means,” in Neural networks: Tricks of the trade. Springer, 2012, pp. 561–580.
[17] A. Coates, A. Y. Ng, and H. Lee, “An analysis of single-layer networks in unsupervised feature learning,” in International Conference on Artificial Intelligence and Statistics, 2011, pp. 215–223.
[18] Y. Dai, X. Li, J. Liu, Z. Tong, and L.-Y. Duan, “Generalizable person re-identification with relevance-aware mixture of experts,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 16 145–16 154.
[19] Z. Dai, M. Chen, X. Gu, S. Zhu, and P. Tan, “Batch dropblock network for person re-identification and beyond,” in Proceedings of the IEEE International Conference on Computer Vision, 2019, pp. 3691–3701.
[20] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A large-scale hierarchical image database,” in 2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009, pp. 248–255.
[21] W. Deng, L. Zheng, Q. Ye, G. Kang, Y. Yang, and J. Jiao, “Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 994–1003.
[22] Z. Deng, A. Vahdat, H. Hu, and G. Mori, “Structure inference machines: Recurrent neural networks for analyzing relations in group activity recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 4772–4781.
[23] M. Dikmen, E. Akbas, T. S. Huang, and N. Ahuja, “Pedestrian recognition with a learned metric,” in Computer Vision–ACCV 2010. Springer, 2011, pp. 501–512.
[24] D. Erhan, Y. Bengio, A. Courville, P.-A. Manzagol, P. Vincent, and S. Bengio, “Why does unsupervised pre-training help deep learning?” Journal of Machine Learning Research, vol. 11, no. Feb, pp. 625–660, 2010.
[25] M. Farenzena, L. Bazzani, A. Perina, V. Murino, and M. Cristani, “Person re-identification by
symmetry-driven accumulation of local features,” in Computer Vision and Pattern Recognition
(CVPR), 2010 IEEE Conference on. IEEE, 2010, pp. 2360–2367.
[26] Y. Fu, Y. Wei, G. Wang, Y. Zhou, H. Shi, and T. S. Huang, “Self-similarity grouping: A simple
unsupervised cross domain adaptation approach for person re-identification,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 6112–6121.
[27] Q. Gao, F. Gao, H. Zhang, X.-J. Hao, and X. Wang, “Two-dimensional maximum local variation based on image euclidean distance for face recognition,” Image Processing, IEEE Transactions on, vol. 22, no. 10, pp. 3807–3817, 2013.
[28] D. Gray and H. Tao, “Viewpoint invariant pedestrian recognition with an ensemble of localized features,” in Computer Vision–ECCV 2008. Springer, 2008, pp. 262–275.
[29] G. Gu, B. Ko, and H.-G. Kim, “Proxy synthesis: Learning with synthetic classes for deep metric learning,” arXiv preprint arXiv:2103.15454, 2021.
[30] R. Hadsell, S. Chopra, and Y. LeCun, “Dimensionality reduction by learning an invariant mapping,” in Computer vision and pattern recognition, 2006 IEEE computer society conference on, vol. 2. IEEE, 2006, pp. 1735–1742.
[31] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778.
[32] A. Hermans, L. Beyer, and B. Leibe, “In defense of the triplet loss for person re-identification,” arXiv preprint arXiv:1703.07737, 2017.
[33] M. Hirzer, C. Beleznai, P. M. Roth, and H. Bischof, “Person re-identification by descriptive and discriminative classification,” in Proceedings of the Scandinavian Conference on Image Analysis. Springer, 2011, pp. 91–102.
[34] M. Hirzer, P. M. Roth, M. K ̈ostinger, and H. Bischof, “Relaxed pairwise learned metric for person re-identification,” in Computer Vision–ECCV 2012. Springer, 2012, pp. 780–793.
[35] M. S. Ibrahim, S. Muralidharan, Z. Deng, A. Vahdat, and G. Mori, “A hierarchical deep temporal model for group activity recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1971–1980.
[36] J. Jia, Q. Ruan, and T. M. Hospedales, “Frustratingly easy person re-identification: Generalizing person re-id in practice,” in Proceedings of the British Machine Vision Conference, vol. 2, 2019.
[37] X. Jin, C. Lan, W. Zeng, Z. Chen, and L. Zhang, “Style normalization and restitution for generalizable person re-identification,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3143–3152.
[38] X.-Y. Jing, X. Zhu, F. Wu, R. Hu, X. You, Y. Wang, H. Feng, and J.-Y. Yang, “Super-resolution person re-identification with semi-coupled low-rank discriminant dictionary learning,” IEEE Transactions on Image Processing, vol. 26, no. 3, pp. 1363–1378, 2017.
[39] E. Kodirov, T. Xiang, and S. Gong, “Dictionary learning with iterative laplacian regularisation for unsupervised person re-identification.” in BMVC, vol. 3, 2015, p. 8.
[40] M. Kostinger, M. Hirzer, P. Wohlhart, P. M. Roth, and H. Bischof, “Large scale metric learning from equivalence constraints,” in Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012, pp. 2288–2295.
[41] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” in Advances in neural information processing systems, 2012, pp. 1097–1105.
[42] T. Lan, Y. Wang, W. Yang, and G. Mori, “Beyond actions: Discriminative models for contextual group activities,” in Advances in neural information processing systems, 2010, pp. 1216–1224.
[43] S. Lazebnik, C. Schmid, and J. Ponce, “Beyond bags of features: Spatial pyramid matching
for recognizing natural scene categories,” in Proceedings of the 2006 IEEE Computer Society
Conference on Computer Vision and Pattern Recognition - Volume 2, ser. CVPR ’06.
Washington, DC, USA: IEEE Computer Society, 2006, pp. 2169–2178. [Online]. Available:
http://dx.doi.org/10.1109/CVPR.2006.68
[44] D. Li, X. Chen, Z. Zhang, and K. Huang, “Learning deep context-aware features over body and latent parts for person re-identification,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 384–393.
[45] S. Li, M. Shao, and Y. Fu, “Cross-view projective dictionary learning for person re-identification.” in IJCAI, 2015, pp. 2155–2161.
[46] W. Li and X. Wang, “Locally aligned feature transforms across views,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 3594–3601.
[47] W. Li, R. Zhao, and X. Wang, “Human reidentification with transferred metric learning,” in Computer Vision–ACCV 2012. Springer, 2013, pp. 31–44.
[48] W. Li, R. Zhao, T. Xiao, and X. Wang, “Deepreid: Deep filter pairing neural network for person re-identification,” in CVPR, 2014.
[49] Z. Li and D. Miao, “Sequential end-to-end network for efficient person search,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 3, 2021, pp. 2011–2019.
[50] M. Liao, G. Pang, J. Huang, T. Hassner, and X. Bai, “Mask textspotter v3: Segmentation proposal network for robust scene text spotting,” in Proceedings of the European Conference on Computer Vision (ECCV), 2020.
[51] C.-S. Lin, Y.-C. Cheng, and Y.-C. F. Wang, “Domain generalized person re-identification via cross-domain episodic learning,” in 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, 2021, pp. 6758–6763.
[52] C. Liu, C. C. Loy, S. Gong, and G. Wang, “POP: Person re-identification post-rank optimisation,” in Computer Vision (ICCV), 2013 IEEE International Conference on. IEEE, 2013, pp. 441–448.
[53] C. Liu, S. Gong, and C. C. Loy, “On-the-fly feature importance mining for person re-identification,”Pattern Recognition, vol. 47, no. 4, pp. 1602–1615, 2014.
[54] X. Liu, M. Song, D. Tao, X. Zhou, C. Chen, and J. Bu, “Semi-supervised coupled dictionary learning for person re-identification,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 3550–3557.
[55] C. C. Loy, T. Xiang, and S. Gong, “Time-delayed correlation analysis for multi-camera activity understanding,” International Journal of Computer Vision, vol. 90, no. 1, pp. 106–129, 2010.
[56] H. Luo, W. Jiang, Y. Gu, F. Liu, X. Liao, S. Lai, and J. Gu, “A strong baseline and batch normalization neck for deep person re-identification,” IEEE Transactions on Multimedia, vol. 22, no. 10, pp. 2597–2609, 2019.
[57] B. Ma, Y. Su, F. Jurie et al., “BiCov: a novel image representation for person re-identification and face verification,” in British Machive Vision Conference, 2012.
[58] A. Mignon and F. Jurie, “PCCA: A new approach for distance learning from sparse pairwise constraints,” in Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. IEEE, 2012, pp. 2666–2672.
[59] Y. Movshovitz-Attias, A. Toshev, T. K. Leung, S. Ioffe, and S. Singh, “No fuss distance metric learning using proxies,” in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 360–368.
[60] R. R. A. Pramono, Y.-T. Chen, and W.-H. Fang, “Hierarchical self-attention network for action localization in videos,” in Proceedings of the IEEE International Conference on Computer Vision, 2019, pp. 61–70.
[61] R. C. H. Pribadi and H.-K. Pao, “Sparse tree structured representation for re-identification,” Pattern Recognition, vol. 60, pp. 394–404, 2016.
[62] B. Prosser, W.-S. Zheng, S. Gong, T. Xiang, and Q. Mary, “Person re-identification by support vector ranking.” in BMVC, vol. 1, no. 3, 2010, p. 5.
[63] D. Purwanto, Y.-T. Chen, and W.-H. Fang, “First-person action recognition with temporal pooling and hilbert–huang transform,” IEEE Transactions on Multimedia, vol. 21, no. 12, pp. 3122–3135, 2019.
[64] X. Qian, Y. Fu, T. Xiang, Y.-G. Jiang, and X. Xue, “Leader-based multi-scale attention deep architecture for person re-identification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019.
[65] T. Shu, S. Todorovic, and S.-C. Zhu, “Cern: Confidence-energy recurrent network for group activity recognition,” arXiv preprint arXiv:1704.03058, 2017.
[66] J. Song, Y. Yang, Y.-Z. Song, T. Xiang, and T. M. Hospedales, “Generalizable person re-identification by domain-invariant mapping network,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 719–728.
[67] A. Subramaniam, M. Chatterjee, and A. Mittal, “Deep neural networks with inexact matching for person re-identification,” in Advances in Neural Information Processing Systems, 2016, pp. 2667–2675.
[68] Y. Suh, J. Wang, S. Tang, T. Mei, and K. M. Lee, “Part-aligned bilinear representations for person re-identification,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 402–419.
[69] Y. Sun, L. Zheng, Y. Li, Y. Yang, Q. Tian, and S. Wang, “Learning part-based convolutional features for person re-identification,” IEEE transactions on pattern analysis and machine intelligence, 2019.
[70] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2818–2826.
[71] R. Vezzani, D. Baltieri, and R. Cucchiara, “People reidentification in surveillance and forensics: A survey,” ACM Computing Surveys (CSUR), vol. 46, no. 2, p. 29, 2013.
[72] H. Wang, S. Gong, and T. Xiang, “Unsupervised learning of generative topic saliency for person re-identification,” in British Machive Vision Conference, 2014.
[73] L. Wang, Y. Zhang, and J. Feng, “On the euclidean distance of images,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 27, no. 8, pp. 1334–1339, 2005.
[74] X. Wang, “Intelligent multi-camera video surveillance: A review,” Pattern recognition letters, vol. 34, no. 1, pp. 3–19, 2013.
[75] X. Wang and R. Zhao, “Person re-identification: System design and evaluation overview,” in Person Re-Identification. Springer, 2014, pp. 351–370.
[76] L. Wei, S. Zhang, W. Gao, and Q. Tian, “Person transfer gan to bridge domain gap for person re-identification,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2018, pp. 79–88.
[77] T. Xiao, S. Li, B. Wang, L. Lin, and X. Wang, “End-to-end deep learning for person search,” arXiv preprint arXiv:1604.01850, vol. 2, no. 2, 2016.
[78] ——, “Joint detection and identification feature learning for person search,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 3415–3424.
[79] Z. Yang, Z. Wang, W. Xu, X. He, Z. Wang, and Z. Yin, “Region-aware random erasing,” in Proceedings of the IEEE International Conference on Communication Technology, 2019, pp. 1699–1703.
[80] Y. Zhai, S. Lu, Q. Ye, X. Shan, J. Chen, R. Ji, and Y. Tian, “Ad-cluster: Augmented discriminative clustering for domain adaptive person re-identification,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9021–9030.
[81] Z. Zhang, C. Lan, W. Zeng, X. Jin, and Z. Chen, “Relation-aware global attention for person re-identification,” in Proceedings of the ieee/cvf conference on computer vision and pattern recognition, 2020, pp. 3186–3195.
[82] R. Zhao, W. Ouyang, and X. Wang, “Unsupervised salience learning for person re-identification,” in Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. IEEE, 2013, pp. 3586–3593.
[83] K. Zheng, W. Liu, L. He, T. Mei, J. Luo, and Z.-J. Zha, “Group-aware label transfer for domain
adaptive person re-identification,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 5310–5319.
[84] L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, and Q. Tian, “Scalable person re-identification: A benchmark,” in Computer Vision, IEEE International Conference on, 2015.
[85] L. Zheng, H. Zhang, S. Sun, M. Chandraker, Y. Yang, and Q. Tian, “Person re-identification in the wild,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1367–1376.
[86] W.-S. Zheng, S. Gong, and T. Xiang, “Reidentification by relative distance comparison,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 35, no. 3, pp. 653–668, 2013.
[87] Z. Zhong, L. Zheng, D. Cao, and S. Li, “Re-ranking person re-identification with k-reciprocal encoding,” in CVPR, 2017.
[88] Z. Zhong, L. Zheng, S. Li, and Y. Yang, “Generalizing a person retrieval model hetero-and homogeneously,” in Proceedings of the European Conference on Computer Vision, 2018, pp. 172–188.
[89] Z. Zhong, L. Zheng, Z. Luo, S. Li, and Y. Yang, “Invariance matters: Exemplar memory for domain adaptive person re-identification,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 598–607.
[90] Z. Zhong, L. Zheng, G. Kang, S. Li, and Y. Yang, “Random erasing data augmentation,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, 2020, pp. 13 001–13 008.