Centralized embedding hypersphere feature learning for person re-identification

References

• Zhong Z, Zheng L, Zheng Z, et al. Camera style adaptation for person re-identification. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018. p. 5157–5166.
   Google Scholar
• Wang Y, Wang Z, Jia W, et al. Joint learning of body and part representation for person re-identification. IEEE Access. 2018;6:44199–44210. doi: 10.1109/ACCESS.2018.2864588
   Web of Science ®Google Scholar
• Chen Y, Zhu X, Gong S. Person re-identification by deep learning multi-scale representations. IEEE International Conference on Computer Vision Workshops (ICCVW); 2018. p. 2590–2600.
   Google Scholar
• Wei L, Zhang S, Gao W, et al. Person transfer gan to bridge domain gap for person re-identification. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018, p. 79–88.
   Google Scholar
• Zhu F, Kong X, Zheng L, et al. Part-based deep hashing for large-scale person re-identification[J]. IEEE Trans Image Process. 2017;26(10):4806–4817. doi: 10.1109/TIP.2017.2695101
   PubMed Web of Science ®Google Scholar
• Lv J, Chen W, Li Q, et al. Unsupervised cross-dataset person re-identification by transfer learning of spatial-temporal patterns. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018. p. 7948–7956.
   Google Scholar
• Zheng Z, Zheng L, Yang Y. Pedestrian alignment network for large-scale person re-identification [J]. IEEE Trans Circuits Syst Video Technol. 2018. DOI:10.1109/TCSVT.2018.2873599
   PubMedGoogle Scholar
• Oh Song H, Xiang Y, Jegelka S, et al. Deep metric learning via lifted structured feature embedding. Proceedings Computer Vision Pattern Recognition. (CVPR); 2016. p. 4004–4012.
   Google Scholar
• Hermans A, Beyer L, Leibe B. In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737, 2017.
   Google Scholar
• Song HO, Jegelka S, Rathod V, et al. Deep metric learning via facility location. Proceedings Computer Vision Pattern Recognition. (CVPR); 2017. p. 5382–5390.
   Google Scholar
• Liao S, Hu Y, Zhu X, et al. Person re-identification by local maximal occurrence representation and metric learning. Proceedings Computer Vision Pattern Recognition. (CVPR); 2015. p. 2197-2206.
   Google Scholar
• Zhao R, Ouyang W, Wang X. Person re-identification by salience matching. Proceedings Computer Vision Pattern Recognition; 2013. p. 2528–2535.
   Google Scholar
• Zhao R, Ouyang W, Wang X. Unsupervised salience learning for person reidentification. Proceedings Computer Vision Pattern Recognition. (ICCV); 2013. p. 3586–3593.
   Google Scholar
• Gong A, Qiu Q, Sapiro G. Virtual CNN branching: efficient feature ensemble for person re-identification. arXiv preprint arXiv:1803.05872, 2018.
   Google Scholar
• Li W, Zhu X, Gong S. Person re-identification by deep joint learning of multi-loss classification Proceedings of the International Joint Conference on Artificial Intelligence. (IJCAI); 2017. p. 2194–2200.
   Google Scholar
• Schroff F, Kalenichenko D, Philbin J. Facenet: a unified embedding for face recognition and clustering. Proceedings Computer Vision Pattern Recognition. (CVPR); 2015. pp. 815–823.
   Google Scholar
• Chen W, Chen X, Zhang J, et al. Beyond triplet loss: a deep quadruplet network for person re-identification. Proceedings Computer Vision Pattern Recognitiont. (CVPR); 2017. p. 403–412.
   Google Scholar
• Ristani E, Tomasi C. Features for multi-target multi-camera tracking and re-identification. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018. p. 6036–6046.
   Google Scholar
• Bak S, Carr P. One-shot metric learning for person re-identification. Proceedings Computer Vision Pattern Recognition. (CVPR); 2017. p. 2990–2999.
   Google Scholar
• Wang J, Zhou F, Wen S, et al. Deep metric learning with angular loss. Proceedings International Conference Computer Vision (ICCV); 2017. p. 2593–2601.
   Google Scholar
• Fan X, Jiang W, Luo H, et al. SphereReID: deep hypersphere manifold embedding for person re-identification. J Vis Commun Image Represent. 2019;60:51–58. doi: 10.1016/j.jvcir.2019.01.010
   Web of Science ®Google Scholar
• Qi X, Zhang L. Face recognition via centralized coordinate learning. arXiv preprint arXiv:1801.05678, 2018.
   Google Scholar
• Wang H, Wang Y, Zhou Z, et al. CosFace: large margin cosine loss for deep face recognition. Proceedings Computer Vision Pattern Recognition (CVPR); 2018, p. 5265–5274.
   Google Scholar
• Wang F, Liu W, Liu H, et al. Additive margin softmax for face verification. IEEE Signal Process Lett. 2018;25:926–930. doi: 10.1109/LSP.2018.2822810
   Web of Science ®Google Scholar
• Deng J, Guo J, Zafeiriou S. ArcFace: additive angular margin loss for deep face recognition. arXiv preprint arXiv:1801.07698, 2018.
   Google Scholar
• Zheng L, Shen L, Tian L, et al. Scalable person re-identification: a benchmark. Proceedings International Conference Computer Vision (ICCV); 2015. p. 1116–1124.
   Google Scholar
• Zheng Z, Zheng L, Yang Y. Unlabeled samples generated by gan improve the person re-identification baseline in vitro. Proceedings International Conference Computer Vision (ICCV); 2017. p. 3774–3782.
   Google Scholar
• Ristani E, Solera F, Zou R, et al. Performance measures and a data set for multi-target, multi-camera tracking. Proceedings European Conference Computer Vision. (ECCV); 2016. p. 17–35.
   Google Scholar
• Wei L, Zhang S, Yao H, et al. Glad: Global-local-alignment descriptor for pedestrian retrieval. Proceedings of the 2017 ACM on Multimedia Conference; 2017. p. 420–428.
   Google Scholar
• He L, Liang J, Li H, et al. Deep spatial feature reconstruction for partial person re-identification: freestyle approach. Proceedings of the Computer Vision Pattern Recognition. (CVPR); 2018. p. 7073–7082.
   Google Scholar
• Li W, Zhu X, Gong S. Harmonious attention network for person re-identification. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018. p. 2285–2294.
   Google Scholar
• Qian X, Fu Y, Jiang Y, et al. Multi-scale deep learning architectures for person re-identification. Proceedong International Conference Computer Vision. (ICCV); 2017. p. 5399–5408.
   Google Scholar
• Guo J, Zhang Y, Huang Z, et al. Person re-identification by weighted integration of sparse and collaborative representation. IEEE Access. 2017;5:21632–21639. doi: 10.1109/ACCESS.2017.2757028
   Web of Science ®Google Scholar
• Su C, Li J, Zhang S, et al. Pose-driven deep convolutional model for person re-identification. Proceedings International Conference Computer Vision. (ICCV); 2017. p. 3980–3989.
   Google Scholar
• Chen Y, Zhu X, Zheng W, et al. Person re-identification by camera correlation aware feature augmentation. IEEE Trans Pattern Analysis & Machine Intelligence. 2017;40(2):392–408. doi: 10.1109/TPAMI.2017.2666805
   PubMed Web of Science ®Google Scholar
• Kalayeh M, Basaran E, Gokmen M. Human semantic parsing for person re-identification. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018. p. 6036–6046.
   Google Scholar
• Xu J, Zhao R, Zhu F, et al. Attention-aware compositional network for person re-identification. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018. p. 2119–2128.
   Google Scholar
• Sarfraz M, Schumann A, Eberle A, et al. A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018. p. 420-429.
   Google Scholar
• Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. Neural Information Processing Systems. (NIPS); 2014. p. 2672–2680.
   Google Scholar
• Zhu F, Kong X, Fu H, et al. Pseudo-positive regularization for deep person re-identification. Multimedia Syst. 2017;7:1–13.
   Google Scholar
• Liu J, Ni B, Yan Y, et al. Pose transferrable person re-identification. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018. p. 4099-4108.
   Google Scholar
• Huang H, Li D, Zhang Z, et al. Adversarially occluded samples for person re-identification. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018. p. 5098–5107.
   Google Scholar
• Deng W, Zheng L, Ye Q, et al. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. Proceedings Computer Vision Pattern Recognition. (CVPR); 2018. p. 994-1003.
   Google Scholar
• Huang Y, Xu J, Wu Q, et al. Multi-pseudo regularized label for generated data in person Re-identification. IEEE Trans Image Processing (TIP). 2019;28(3):1391–1403. doi: 10.1109/TIP.2018.2874715
   Web of Science ®Google Scholar
• Zhong Z, Zheng L, Cao D, et al. Re-ranking person reidentification with k-reciprocal encoding. Proceedings Computer Vision Pattern Recognition (CVPR); 2017. p. 3652–3661.
   Google Scholar
• Zhong Z, Zheng L, Kang G, et al. Random erasing data augmentation. arXiv preprint arXiv:1708.04896, 2017.
   Google Scholar
• Liu W, Wen Y, Yu Z, et al. Large-margin softmax loss for convolutional neural networks International Conference on International Conference on Machine Learning; 2016. p. 507–516.
   Google Scholar
• Liu W, Wen Y, Yu Z, et al. SphereFace: deep hypersphere embedding for face recognition. Proceedings Computer Vision Pattern Recognition. (CVPR); 2017. p. 6738–6746.
   Google Scholar
• Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems; 2012. p. 1097–1105.
   Google Scholar
• Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions. Proceedings Computer Vision Pattern Recognition. (CVPR); 2015. p. 1-9.
   Google Scholar
• He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. Proceedings Computer Vision Pattern Recognition. (CVPR); 2016. p. 770–778.
   Google Scholar
• Huang G, Liu Z, Maaten L, et al. Densely connected convolutional networks. Proceedings Computer Vision Pattern Recognition. (CVPR); 2017. p. 4700–4708.
   Google Scholar
• Harwood B, Kumar V, Carneiro G, et al. Smart mining for deep metric learning. Proceedings International Conference Computer Vision (ICCV); 2017. p. 2821–2829.
   Google Scholar
• Almazan J, Gajic B, Murray N, et al. “Re-ID done right: towards good practices for person re-identification,” arXiv preprint arXiv:1801.05339, 2018.
   Google Scholar
• Sun Y, Zheng L, Yang Y, et al. Beyond part models: person retrieval with refined part pooling. Proceedings European Conference Computer Vision (ECCV); 2018. p. 501–518.
   Google Scholar