E. Ahmed, M. Jones, and T. K. Marks, An improved deep learning architecture for person re-identification, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.3908-3916, 2015.

R. Arandjelovic, P. Gronat, A. Torii, T. Pajdla, and J. Sivic, Netvlad: Cnn architecture for weakly supervised place recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.5297-5307, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01242052

A. Babenko, A. Slesarev, A. Chigorin, and V. Lempitsky, Neural codes for image retrieval, European conference on computer vision, pp.584-599, 2014.

S. Bak, E. Corvee, F. Bremond, and M. Thonnat, Person re-identification using spatial covariance regions of human body parts, IEEE International Conference on Advanced Video and Signal Based Surveillance, 2010.
URL : https://hal.archives-ouvertes.fr/inria-00496116

S. Bak, S. Zaidenberg, B. Boulay, and F. Bremond, Improving person reidentification by viewpoint cues, Advanced Video and Signal Based Surveillance (AVSS), pp.175-180, 2014.
URL : https://hal.archives-ouvertes.fr/hal-01004390

L. Bazzani, M. Cristani, A. Perina, M. Farenzena, and V. Murino, Multipleshot person re-identification by hpe signature, 20th International Conference on, pp.1413-1416, 2010.

Y. Bengio, P. Simard, and P. Frasconi, Learning long-term dependencies with gradient descent is difficult, IEEE transactions on neural networks, vol.5, issue.2, pp.157-166, 1994.

J. Bromley, I. Guyon, Y. Lecun, E. Säckinger, and R. Shah, Signature verification using a" siamese" time delay neural network, Advances in Neural Information Processing Systems, pp.737-744, 1994.

C. Burges, T. Shaked, E. Renshaw, A. Lazier, M. Deeds et al., Learning to rank using gradient descent, ICML, pp.89-96, 2005.

C. J. Burges, R. Ragno, and Q. V. Le, Learning to rank with nonsmooth cost functions, NIPS, pp.193-200, 2007.

Y. Cai and G. Medioni, Exploring context information for inter-camera multiple target tracking, Applications of Computer Vision (WACV), 2014 IEEE Winter Conference on, pp.761-768, 2014.

Y. Cai, V. Takala, and M. Pietikainen, Matching groups of people by covariance descriptor, Pattern Recognition (ICPR), 2010 20th International Conference on, pp.2744-2747, 2010.

Z. Cao, T. Qin, T. Liu, M. Tsai, L. et al., Learning to rank: from pairwise approach to listwise approach, ICML, pp.129-136, 2007.

W. Chen, X. Chen, J. Zhang, and K. Huang, Beyond triplet loss: a deep quadruplet network for person re-identification, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), vol.2, 2017.

W. Chen, X. Chen, J. Zhang, and K. Huang, A multi-task deep network for person re-identification, AAAI, pp.3988-3994, 2017.

Y. Chen, X. Zhu, and S. Gong, Person re-identification by deep learning multi-scale representations, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.2590-2600, 2017.

D. Cheng, Y. Gong, S. Zhou, J. Wang, and N. Zheng, Person re-identification by multi-channel parts-based cnn with improved triplet loss function, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.1335-1344, 2016.

D. S. Cheng, M. Cristani, M. Stoppa, L. Bazzani, and V. Murino, Custom pictorial structures for re-identification, Bmvc, vol.1, p.6, 2011.

S. Chopra, R. Hadsell, and Y. Lecun, Learning a similarity metric discriminatively, with application to face verification, Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol.1, pp.539-546, 2005.

O. Chum, J. Philbin, J. Sivic, M. Isard, and A. Zisserman, Total recall: Automatic query expansion with a generative feature model for object retrieval, IEEE 11th International Conference on, pp.1-8, 2007.

Y. Deng, P. Luo, C. C. Loy, and X. Tang, Pedestrian attribute recognition at far distance, Proc. of the ACM international conference on Multimedia, pp.789-792, 2014.

Y. Deng, P. Luo, C. C. Loy, and X. Tang, Learning to recognize pedestrian attribute, 2015.

M. Dikmen, E. Akbas, T. S. Huang, A. , and N. , Pedestrian recognition with a learned metric, Asian conference on Computer vision, pp.501-512, 2010.
DOI : 10.1007/978-3-642-19282-1_40
URL : http://vision.ai.uiuc.edu/publications/dikmen_accv10.pdf

S. Ding, L. Lin, G. Wang, and H. Chao, Deep feature learning with relative distance comparison for person re-identification, Pattern Recognition, vol.48, issue.10, pp.2993-3003, 2015.
DOI : 10.1016/j.patcog.2015.04.005
URL : http://arxiv.org/pdf/1512.03622

K. Duan, D. Parikh, D. Crandall, and K. Grauman, Discovering localized attributes for fine-grained recognition, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.3474-3481, 2012.

M. Farenzena, L. Bazzani, A. Perina, V. Murino, and M. Cristani, Person re-identification by symmetry-driven accumulation of local features, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.2360-2367, 2010.

I. Fogel and D. Sagi, Gabor filters as texture discriminator, Biological cybernetics, vol.61, issue.2, pp.103-113, 1989.
DOI : 10.1007/bf00204594

J. García, N. Martinel, G. L. Foresti, A. Gardel, and C. Micheloni, Person orientation and feature distances boost re-identification, 22nd International Conference on, pp.4618-4623, 2014.

N. Gheissari, T. B. Sebastian, and R. Hartley, Person reidentification using spatiotemporal appearance, Computer Vision and Pattern Recognition, vol.2, pp.1528-1535, 2006.
DOI : 10.1109/cvpr.2006.223

I. Goodfellow, J. Pouget-abadie, M. Mirza, B. Xu, D. Warde-farley et al., Generative adversarial nets, Advances in neural information processing systems, pp.2672-2680, 2014.

A. Gordo, J. Almazán, J. Revaud, and D. Larlus, Deep image retrieval: Learning global representations for image search, European Conference on Computer Vision, pp.241-257, 2016.
DOI : 10.1007/978-3-319-46466-4_15
URL : http://arxiv.org/pdf/1604.01325

D. Gray, S. Brennan, and H. Tao, Evaluating appearance models for recognition, reacquisition, and tracking, Proc. of International Workshop on Performance Evaluation for Tracking and Surveillance (PETS), vol.3, 2007.

D. Gray and H. Tao, Viewpoint invariant pedestrian recognition with an ensemble of localized features, Proc. of the European Conference on Computer Vision (ECCV), pp.262-275, 2008.

A. Haque, A. Alahi, and L. Fei-fei, Recurrent attention models for depthbased person identification, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1229-1238, 2016.
DOI : 10.1109/cvpr.2016.138
URL : http://arxiv.org/pdf/1611.07212

J. Håstad and M. Goldmann, On the power of small-depth threshold circuits, Computational Complexity, vol.1, issue.2, pp.113-129, 1991.

K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, pp.770-778, 2016.
DOI : 10.1109/cvpr.2016.90
URL : http://arxiv.org/pdf/1512.03385

R. Herbrich, Large margin rank boundaries for ordinal regression. Advances in large margin classifiers, pp.115-132, 2000.

A. Hermans, L. Beyer, and B. Leibe, defense of the triplet loss for person re-identification, 2017.

M. Hirzer, C. Beleznai, P. M. Roth, and H. Bischof, Person re-identification by descriptive and discriminative classification, Scandinavian conference on Image analysis, pp.91-102, 2011.
DOI : 10.1007/978-3-642-21227-7_9
URL : https://link.springer.com/content/pdf/10.1007%2F978-3-642-21227-7_9.pdf

K. Hornik, M. Stinchcombe, and H. White, Multilayer feedforward networks are universal approximators, Neural networks, vol.2, issue.5, pp.359-366, 1989.
DOI : 10.1016/0893-6080(89)90020-8

M. Jaderberg, K. Simonyan, and A. Zisserman, Spatial transformer networks, Advances in neural information processing systems, pp.2017-2025, 2015.

O. Javed, Z. Rasheed, K. Shafique, and M. Shah, Tracking across multiple cameras with disjoint views, Proceedings of the Ninth IEEE International Conference on Computer Vision, vol.2, p.952, 2003.

H. Jegou, M. Douze, and C. Schmid, Hamming embedding and weak geometric consistency for large scale image search, European conference on computer vision, pp.304-317, 2008.
URL : https://hal.archives-ouvertes.fr/inria-00316866

H. Jégou, M. Douze, C. Schmid, and P. Pérez, Aggregating local descriptors into a compact image representation, CVPR, pp.3304-3311, 2010.

Y. Kalantidis, C. Mellina, and S. Osindero, Cross-dimensional weighting for aggregated deep convolutional features, European Conference on Computer Vision, pp.685-701, 2016.

S. Khamis, C. Kuo, V. K. Singh, V. D. Shet, and L. S. Davis, Joint learning for attribute-consistent person re-identification, ECCV Workshops, pp.134-146, 2014.

D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, ICML, 2015.

M. Koestinger, M. Hirzer, P. Wohlhart, P. M. Roth, and H. Bischof, Large scale metric learning from equivalence constraints, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.2288-2295, 2012.

A. Krizhevsky, I. Sutskever, and G. E. Hinton, Imagenet classification with deep convolutional neural networks, Proc. of Advances in neural information processing systems (NIPS), pp.1097-1105, 2012.

N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar, Attribute and simile classifiers for face verification, Proc. of the International Conference on Computer Vision (ICCV), pp.365-372, 2009.

R. Layne, T. M. Hospedales, and S. Gong, Attributes-based re-identification, Person Re-Identification, pp.93-117, 2014.

R. Layne, T. M. Hospedales, S. Gong, M. , and Q. , Person re-identification by attributes, Proc. of the British Machine Vision Conference (BMVC), vol.2, p.8, 2012.

Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, Gradient-based learning applied to document recognition, Proceedings of the IEEE, vol.86, issue.11, pp.2278-2324, 1998.

A. Li, L. Liu, Y. , and S. , Person re-identification by attribute-assisted clothes appearance, Person Re-Identification, pp.119-138, 2014.

D. Li, X. Chen, and K. Huang, Multi-attribute learning for pedestrian attribute recognition in surveillance scenarios, Proc. of the Asian Conference on Pattern Recognition (ACPR, 2015.

D. Li, X. Chen, Z. Zhang, and K. Huang, Learning deep context-aware features over body and latent parts for person re-identification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.384-393, 2017.

H. Li, J. Chen, H. Lu, C. , and Z. , Cnn for saliency detection with low-level feature integration, Neurocomputing, vol.226, pp.212-220, 2017.

S. Li, S. Bak, P. Carr, W. , and X. , Diversity regularized spatiotemporal attention for video-based person re-identification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.369-378, 2018.

W. Li and X. Wang, Locally aligned feature transforms across views, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.3594-3601, 2013.

W. Li, R. Zhao, W. , and X. , Human reidentification with transferred metric learning, ACCV, 2012.

W. Li, R. Zhao, T. Xiao, W. , and X. , Deepreid:deep filter pairing neural network for person re-identification, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.152-159, 2014.

W. Li, X. Zhu, and S. Gong, Person re-identification by deep joint learning of multi-loss classification, International Joint Conference on Artificial Intelligence, 2017.

W. Li, X. Zhu, and S. Gong, Harmonious attention network for person re-identification, CVPR, vol.1, p.2, 2018.

S. Liao, Y. Hu, X. Zhu, and S. Z. Li, Person re-identification by local maximal occurrence representation and metric learning, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.2197-2206, 2015.

S. Liao, G. Zhao, V. Kellokumpu, M. Pietikäinen, and S. Z. Li, Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.1301-1306, 2010.

Z. Lin and L. S. Davis, Learning pairwise dissimilarity profiles for appearance recognition in visual surveillance, International symposium on visual computing, pp.23-34, 2008.

G. Lisanti, N. Martinel, A. Del-bimbo, and G. L. Foresti, Group reidentification via unsupervised transfer of sparse features encoding, Proc. of the IEEE International Conference on International Conference on Computer Vision (ICCV), 2017.

G. Lisanti, I. Masi, D. Bimbo, and A. , Matching people across camera views using kernel canonical correlation analysis, Proceedings of the International Conference on Distributed Smart Cameras, p.10, 2014.

H. Liu, J. Feng, M. Qi, J. Jiang, Y. et al., End-to-end comparative attention networks for person re-identification, IEEE Transactions on Image Processing, 2017.

J. Liu, B. Kuipers, and S. Savarese, Recognizing human actions by attributes, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.3337-3344, 2011.

J. Liu, B. Ni, Y. Yan, P. Zhou, S. Cheng et al., Pose transferrable person re-identification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.4099-4108, 2018.

X. Liu, M. Song, D. Tao, X. Zhou, C. Chen et al., Semi-supervised coupled dictionary learning for person re-identification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3550-3557, 2014.

D. G. Lowe, Object recognition from local scale-invariant features, Computer vision, 1999. The proceedings of the seventh IEEE international conference on, vol.2, pp.1150-1157, 1999.

C. C. Loy, T. Xiang, and S. Gong, Multi-camera activity correlation analysis, Computer Vision and Pattern Recognition, pp.1988-1995, 2009.

A. Lumini, L. Nanni, and S. Ghidoni, Deep featrues combined with handcrafted features for face recognition, International Journal of Computer Research, vol.23, issue.2, p.123, 2016.

B. Ma, Y. Su, J. , and F. , Local descriptors encoded by fisher vectors for person re-identification, Proc. of the European Conference on Computer Vision (ECCV), pp.413-422, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00806066

L. Ma, H. Liu, L. Hu, C. Wang, and Q. Sun, Orientation driven bag of appearances for person re-identification, 2016.

L. Ma, X. Yang, and D. Tao, Person re-identification over camera networks using multi-task distance metric learning, IEEE Transactions on Image Processing, vol.23, issue.8, pp.3656-3670, 2014.

D. Makris, T. Ellis, and J. Black, Bridging the gaps between cameras, Proceedings of the 2004 IEEE Computer Society Conference on, vol.2, pp.II-II, 2004.

J. Man and B. Bhanu, Individual recognition using gait energy image, IEEE transactions on pattern analysis and machine intelligence, vol.28, pp.316-322, 2006.

T. Matsukawa, T. Okabe, E. Suzuki, and Y. Sato, Hierarchical gaussian descriptor for person re-identification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1363-1372, 2016.

T. Matsukawa and E. Suzuki, Person re-identification using cnn features learned from combination of attributes, Pattern Recognition (ICPR), 2016 23rd International Conference on, pp.2428-2433, 2016.

N. Mclaughlin, J. M. Del-rincon, and P. C. Miller, Person reidentification using deep convnets with multitask learning, IEEE Transactions on Circuits and Systems for Video Technology, vol.27, pp.525-539, 2017.

N. Mclaughlin, J. Martinez-del-rincon, and P. Miller, Recurrent convolutional network for video-based person re-identification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1325-1334, 2016.

A. Mignon and F. Jurie, Pcca: A new approach for distance learning from sparse pairwise constraints, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.2666-2672, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00806007

M. Munaro, A. Basso, A. Fossati, L. Van-gool, and E. Menegatti, 3d reconstruction of freely moving persons for re-identification with a depth sensor, IEEE International Conference on, pp.4512-4519, 2014.

M. Munaro, A. Fossati, A. Basso, E. Menegatti, and L. Van-gool, One-shot person re-identification with a consumer depth camera, Person Re-Identification, pp.161-181, 2014.

T. Ojala, M. Pietikäinen, and D. Harwood, A comparative study of texture measures with classification based on featured distributions, Pattern recognition, vol.29, issue.1, pp.51-59, 1996.

S. Pedagadi, J. Orwell, S. Velastin, and B. Boghossian, Local fisher discriminant analysis for pedestrian re-identification, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.3318-3325, 2013.

F. Porikli, Inter-camera color calibration by correlation model function, Proceedings. 2003 International Conference on, vol.2, p.133, 2003.

B. J. Prosser, W. Zheng, S. Gong, T. Xiang, M. et al., Person reidentification by support vector ranking, BMVC, vol.2, p.6, 2010.

F. Radenovi´cradenovi´c, G. Tolias, and O. Chum, Cnn image retrieval learns from bow: Unsupervised fine-tuning with hard examples, European Conference on Computer Vision, pp.3-20, 2016.

D. E. Rumelhart, G. E. Hinton, and R. J. Williams, Learning representations by back-propagating errors, nature, vol.323, issue.6088, p.533, 1986.

J. Sánchez, F. Perronnin, T. Mensink, and J. Verbeek, Image classification with the fisher vector: Theory and practice, International journal of computer vision, vol.105, issue.3, pp.222-245, 2013.

M. S. Sarfraz, A. Schumann, Y. Wang, and R. Stiefelhagen, Deep viewsensitive pedestrian attribute inference in an end-to-end model, Proc. of the British Machine Vision Conference (BMVC), 2017.

F. Schroff, D. Kalenichenko, and J. Philbin, Facenet: A unified embedding for face recognition and clustering, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.815-823, 2015.

A. Schumann and R. Stiefelhagen, Person re-identification by deep learning attribute-complementary information, Computer Vision and Pattern Recognition Workshops (CVPRW), pp.1435-1443, 2017.

W. R. Schwartz and L. S. Davis, Learning discriminative appearance-based models using partial least squares, Conference on Computer Graphics and Image Processing (SIBGRAPI), pp.322-329, 2009.

Y. Shen, W. Lin, J. Yan, M. Xu, J. Wu et al., Person re-identification with correspondence structure learning, Proceedings of the IEEE International Conference on Computer Vision, pp.3200-3208, 2015.

H. Shi, Y. Yang, X. Zhu, S. Liao, Z. Lei et al., Embedding deep metric for person re-identification: A study against large variations, European Conference on Computer Vision, pp.732-748, 2016.

K. Simonyan and A. Zisserman, Very deep convolutional networks for large-scale image recognition, 2014.

N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting, Journal of Machine Learning Research, vol.15, issue.1, pp.1929-1958, 2014.

C. Su, S. Zhang, J. Xing, W. Gao, and Q. Tian, Deep attributes driven multi-camera person re-identification, European Conference on Computer Vision, pp.475-491, 2016.

A. Subramaniam, M. Chatterjee, and A. Mittal, Deep neural networks with inexact matching for person re-identification, Advances in Neural Information Processing Systems, pp.2667-2675, 2016.

P. Sudowe, H. Spitzer, and B. Leibe, Person attribute recognition with a jointly-trained holistic cnn model, Proceedings of the IEEE International Conference on Computer Vision Workshops, pp.87-95, 2015.

Y. Sun, L. Zheng, W. Deng, W. , and S. , Svdnet for pedestrian retrieval, Proc. of the IEEE International Conference on International Conference on Computer Vision (ICCV), 2017.

Y. Tian, P. Luo, X. Wang, and X. Tang, Pedestrian detection aided by deep learning semantic tasks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.5079-5087, 2015.

G. Tolias, R. Sicre, and H. Jégou, Particular object retrieval with integral max-pooling of cnn activations, International Conference on Learning Representations, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01842218

O. Tuzel, F. Porikli, and P. Meer, Region covariance: A fast descriptor for detection and classification, European conference on computer vision, pp.589-600, 2006.

N. Ukita, Y. Moriguchi, and N. Hagita, People re-identification across nonoverlapping cameras using group features, Computer Vision and Image Understanding, vol.144, pp.228-236, 2016.

D. A. Vaquero, R. S. Feris, D. Tran, L. Brown, A. Hampapur et al., , 2009.

, Attribute-based people search in surveillance environments, Proc. of Workshop on Applications of Computer Vision (WACV), pp.1-8

R. R. Varior, M. Haloi, W. , and G. , Gated siamese convolutional neural network architecture for human re-identification, Proc. of the IEEE International Conference on European Conference on Computer Vision (ECCV), pp.791-808, 2016.

R. R. Varior, B. Shuai, J. Lu, D. Xu, W. et al., A siamese long short-term memory architecture for human re-identification, Proc. of the European Conference on Computer Vision (ECCV), pp.135-153, 2016.

A. Verma, R. Hebbalaguppe, L. Vig, S. Kumar, and E. Hassan, Pedestrian detection via mixture of cnn experts and thresholded aggregated channel features, Proceedings of the IEEE International Conference on Computer Vision Workshops, pp.163-171, 2015.

F. Wang, W. Zuo, L. Lin, D. Zhang, and L. Zhang, Joint learning of single-image and cross-image representations for person re-identification, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.1288-1296, 2016.

J. Wang, T. Leung, C. Rosenberg, J. Wang, J. Philbin et al., Learning fine-grained image similarity with deep ranking, CVPR, 2014.

J. Wang, Z. Wang, C. Gao, N. Sang, and R. Huang, Deeplist: Learning deep features with adaptive listwise constraint for person reidentification, IEEE Transactions on Circuits and Systems for Video Technology, vol.27, pp.513-524, 2017.

T. Wang, S. Gong, X. Zhu, W. , and S. , Person re-identification by video ranking, European Conference on Computer Vision, pp.688-703, 2014.

X. Wang, G. Doretto, T. Sebastian, J. Rittscher, and P. Tu, Shape and appearance context modeling, Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on, pp.1-8, 2007.

L. Wei and S. K. Shah, Subject centric group feature for person reidentification, CVPR Workshops, pp.28-35, 2015.

L. Wei, S. Zhang, W. Gao, and Q. Tian, Person transfer gan to bridge domain gap for person re-identification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.79-88, 2018.

L. Wu, C. Shen, and A. V. Hengel, Personnet: Person re-identification with deep convolutional neural networks, 2016.

S. Wu, Y. Chen, X. Li, A. Wu, J. You et al., An enhanced deep feature representation for person re-identification, IEEE Winter Conference on Applications of Computer Vision (WACV), pp.1-8, 2016.

F. Xia, T. Liu, J. Wang, W. Zhang, L. et al., Listwise approach to learning to rank: theory and algorithm, ICML, pp.1192-1199, 2008.

B. Xu, N. Wang, T. Chen, L. , and M. , Empirical evaluation of rectified activations in convolutional network, 2015.

Y. Yan, B. Ni, Z. Song, C. Ma, Y. Yan et al., Person re-identification via recurrent feature aggregation, European Conference on Computer Vision, pp.701-716, 2016.

Y. Yang, J. Yang, J. Yan, S. Liao, D. Yi et al., Salient color names for person re-identification, European conference on computer vision, pp.536-551, 2014.

D. Yi, Z. Lei, S. Liao, and S. Z. Li, Deep metric learning for person reidentification, Proc. of the IEEE International Conference on International Conference on Pattern Recognition, pp.34-39, 2014.

J. You, A. Wu, X. Li, and W. Zheng, Top-push video-based person re-identification, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.1345-1353, 2016.

R. Yu, Z. Zhou, S. Bai, and X. Bai, Divide and fuse: A re-ranking approach for person re-identification, Proc. of the British Machine Vision Conference (BMVC), 2017.

L. Zhang, T. Xiang, and S. Gong, Learning a discriminative null space for person re-identification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1239-1248, 2016.

Y. Zhang, B. Li, H. Lu, A. Irie, and X. Ruan, Sample-specific svm learning for person re-identification, Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pp.1278-1287, 2016.

H. Zhao, M. Tian, S. Sun, J. Shao, J. Yan et al., Spindle net: Person re-identification with human body region guided feature decomposition and fusion, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1077-1085, 2017.

L. Zhao, X. Li, J. Wang, and Y. Zhuang, Deeply-learned part-aligned representations for person re-identification, Proc. of the IEEE International Conference on International Conference on Computer Vision (ICCV), 2017.

R. Zhao, W. Ouyang, W. , and X. , Unsupervised salience learning for person re-identification, Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp.3586-3593, 2013.

L. Zheng, Z. Bie, Y. Sun, J. Wang, C. Su et al., Mars: A video benchmark for large-scale person re-identification, European Conference on Computer Vision, pp.868-884, 2016.

L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang et al., Scalable person re-identification: A benchmark, Computer Vision, IEEE International Conference on, 2015.

W. Zheng, S. Gong, and T. Xiang, Associating groups of people, BMVC, 2009.

W. Zheng, S. Gong, and T. Xiang, Person re-identification by probabilistic relative distance comparison, Computer vision and pattern recognition (CVPR), pp.649-656, 2011.

Z. Zheng, L. Zheng, Y. , and Y. , A discriminatively learned cnn embedding for person reidentification, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), vol.14, p.13, 2017.
DOI : 10.1145/3159171
URL : http://arxiv.org/pdf/1611.05666

Z. Zheng, L. Zheng, Y. , and Y. , Unlabeled samples generated by gan improve the person re-identification baseline in vitro, Proc. of the IEEE International Conference on International Conference on Computer Vision (ICCV), 2017.
DOI : 10.1109/iccv.2017.405
URL : https://opus.lib.uts.edu.au/bitstream/10453/118067/4/FF67E427-6528-4081-B0B7-C3EB797E0421.pdf

Z. Zhong, L. Zheng, D. Cao, L. , and S. , Re-ranking person re-identification with k-reciprocal encoding, Proc. of the International Conference on Computer Vision (ICCV), 2017.
DOI : 10.1109/cvpr.2017.389
URL : https://opus.lib.uts.edu.au/bitstream/10453/118077/4/6FE4BDE0-2335-4423-BA25-603F4FFF0AF2.pdf

J. Zhu, S. Liao, Z. Lei, and S. Z. Li, Improve pedestrian attribute classification by weighted interactions from other attributes, Asian Conference on Computer Vision, pp.545-557, 2014.
DOI : 10.1007/978-3-319-16634-6_40

J. Zhu, S. Liao, Z. Lei, and S. Z. Li, Multi-label convolutional neural network based pedestrian attribute classification, Image and Vision Computing, vol.58, pp.224-229, 2017.
DOI : 10.1016/j.imavis.2016.07.004

J. Zhu, S. Liao, Z. Lei, D. Yi, L. et al., Pedestrian attribute classification in surveillance: Database and evaluation, Proc. of the International Conference on Computer Vision (ICCV) Workshops, pp.331-338, 2013.

J. Zhu, S. Liao, D. Yi, Z. Lei, and S. Z. Li, Multi-label cnn based pedestrian attribute learning for soft biometrics, Proc. of the International Conference on Biometrics(ICB), pp.535-540, 2015.
DOI : 10.1109/icb.2015.7139070

. Cheng, 59] ont proposé d'apprendre une fonction Locally-Adaptive Decision (LADF) qui pourrait être considérée comme une fusion d'une distance métrique et d'un seuillage localement adapté. Koestinger et al. [48] ont présenté une métrique appelée KISSME (keep it simple and straight forward metric). La décision "une paire est similaire" est formulée comme un test de ratio de ressemblance. La distance est basée sur la différence entre l'inverse de la matrice de covariance pour les paires similaires et celle des paires dissimilaires. Liao et al. [64] ont proposé d'apprendre un sous-espace dans lequel la variance des paires similaires est minimisée et celle des paires dissimilaires est maximisée, et puis d'appliquer la métrique KISSME dans cet espace réduit. Suivant le grand succès de l'apprentissage profond dans le domaine de vision par ordinateur, des méthodes basées sur les réseaux de neurones à convolution ont été proposées pour la ré-identification de personnes. Yi et al. [128] ont construit un réseau de neurones siamois à convolution. L'image est découpée en trois parties horizontales. Chaque partie est associée à un réseau de neurones à convolution. A la fin, les trois parties sont fusionnées au niveau de leurs scores. DeepReID [61] ont proposé une nouvelle architecture de réseau Filter Pairing Neural Network (FPNN). Ils ont utilisé une couche de "patch matching" pour modéliser le déplacement des parties du corps. Ahmed et al. [1] ont proposé un réseau qui a une paire d'images en entrée et un score de similarité en sortie. Dans leur réseau, ils ont calculé la différence de cartes caractéristiques pour capturer la relation locale entre deux images d'entrée, Un grand nombre de travaux ont été proposés pour l'extraction de caractéristiques. Gray et Tao [33] ont proposé d'utiliser Adaboost pour sélectionner les bonnes caractéristiques dans un ensemble de caractéristiques de couleurs et de textures. Farenzena et al. [26] ont proposé la méthode Symmetry-Driven Accumulation of Local Features (SDALF) dans laquelle la symétrie et l'asymétrie de l'image de personne sont prises en compte pour traiter le problème de point de vue. Ma et al. [76] ont encodé les caractéristiques locales comme un vecteur de Fisher pour créer une représentation globale d'une image, vol.17

, Ré-identification de personne avec les attributs

, L'autre avantage est de rendre le modèle intelligible par l'humain. Cela pourrait permettre de chercher une personne sans image mais avec seulement une description textuelle d'humain. Donc nous proposons un système de ré-identification basé sur CNN et assisté par les attributs. Dans un premier temps, notre méthode effectue l'apprentissage des attributs. L'architecture du réseau de neurones convolutif est constituée de plusieurs couches de « convolutionpooling ». Et puis, les cartes de caractéristiques sont découpées verticalement en 4 parties. Sur chaque partie, différents noyaux de convolutions sont appliqués afin que le réseau apprenne les caractéristiques spécifiques à chaque partie du corps. En plus, notre approche combine les caractéristiques CNN avec une caractéristique de bas niveau LOMO de sorte de régler le problème de grande variation d'apparence visuelle et de location des attributs aux changements de pose ou point de vue. Une fonction de perte « multi-label » est employée pour l'entrainement. Comme les nombres d'exemples positifs (présence des attributs) et négatifs (absence des attributs) sont généralement déséquilibrés, un terme de pondération est introduit dans la fonction de perte. Nos expériences sur les trois benchmarks publics sur la reconnaissance d'attributs, montrent que la méthode proposée améliore l'état de l'art. De plus, en combinant les attributs et les caractéristiques de bas niveau, les résultats s'améliorent, montrant ainsi la complé-mentarité des deux types de caractéristiques, Les attributs sont des propriétés sémantiques et observables dans des images. Une idée principale de cette thèse est de faciliter la ré-identification avec la prise en compte des attributs sémantiques de la personne : vêtements, objets portés, chapeau, lunettes, personnes accompagnantes, etc. L'utilisation de ce type d'attributs présente quelques avantages. L'attribut est plus invariant contre les variations des points de vue que les caractéristiques visuelles de bas niveau

!. Date!de and . Soutenance,

!. Titre!:-résidentification!de!personnes!dans!des!images!par!apprentissage!automatique!-!-nature!:!doctorat!-numéro!d'ordre!:!-!-2018lysei074-!-!-ecole!doctorale!:!infomaths, !. Spécialité!:!informatique, . Resume!:!-la!vidéosurveillance!est!d'une!grande!valeur!pour!la!sécurité!publique.!en!tant!que!l'un!des!plus!importantes!applications!de!-vidéosurveillance, and . Résidentification!de!personnes!est!définie!comme!le!problème!de!l, identification!d'individus!dans!des! images!captées!par!différentes!caméras!de!surveillance!à!champs!nonSrecouvrants.!Cependant,!cette!tâche!est!difficile!à!cause! d'une!série!de!défis!liés!à!l'apparence!de!la!personne,!tels!que!les!variations!de!poses,!de!point!de!vue!et!de!l'éclairage!etc.! ! Pour!régler!ces!différents!problèmes,!dans!cette!thèse,!nous!proposons!plusieurs!approches!basées!sur!l'apprentissage! profond!de!sorte!d'améliorer!de!différentes!manières!la!performance!de!réSidentification.!Dans!la!première!approche,!nous! utilisons!les!attributs!des!piétons!tels!que!genre,!accessoires!et!vêtements.!Nous!proposons!un!système!basé!sur!un!réseau!de! neurones!à!convolution(CNN)!qui!est!composé!de!deux!branches!:!une!pour!la!classification!d'identité!et!l'autre!pour!la! reconnaissance!d'attributs.!Nous!fusionnons!ensuite!ces!deux!branches!pour!la!réSidentification.! ! Deuxièmement,!nous! proposons!un!CNN!prenant!en!compte!différentes!orientations!du!corps!humain.!Le!système!fait!une!estimation!de!l'orientation! et,!de!plus,!combine!les!caractéristiques!de!différentes!orientations!extraites!pour!être!plus!robuste!au!changement!de!point!de! vue.!Comme!troisième!contribution!de!cette!thèse,!nous!proposons!une!nouvelle!fonction!de!coût!basée!sur!une!liste! d'exemples.!Elle!introduit!une!pondération!basée!sur!le!désordre!du!classement!et!permet!d'optimiser!directement!les!mesures! d'évaluation.!Enfin,!pour!un!groupe!de!personnes,!nous!proposons!d'extraire!une!représentation!de!caractéristiques!visuelles! invariante!à!la!position!d'un!individu!dans!une!image!de!group.!Cette!prise!en!compte!de!contexte!de!groupe!réduit!ainsi! l'ambigüité!de!réSidentification.! ! Pour!chacune!de!ces!quatre!contributions,!nous!avons!effectué!de!nombreuses!expériences!sur!les!différentes!bases!de! données!publiques!pour!montrer!l'efficacité!des!approches!proposées.! ! MOTSSCLÉS!:!vision!par!ordinateur,!apprentissage!profond,!réSidentification!de!personne! ! Laboratoire!(s)!de!recherche