{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:43:56Z","timestamp":1784821436616,"version":"3.55.0"},"reference-count":266,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176188"],"award-info":[{"award-number":["62176188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62361166629"],"award-info":[{"award-number":["62361166629"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225113"],"award-info":[{"award-number":["62225113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11263-024-02284-4","type":"journal-article","created":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T12:01:43Z","timestamp":1732363303000},"page":"2410-2440","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Transformer for Object Re-identification: A Survey"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3989-7655","authenticated-orcid":false,"given":"Mang","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuoyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyue","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Crandall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"2284_CR1","unstructured":"(2022). Beluga id 2022. https:\/\/lila.science\/datasets\/beluga-id-2022\/"},{"key":"2284_CR2","unstructured":"(2022). Hyena id 2022. https:\/\/lila.science\/datasets\/hyena-id-2022\/"},{"key":"2284_CR3","unstructured":"(2022). Leopard id 2022. https:\/\/lila.science\/datasets\/leopard-id-2022\/"},{"key":"2284_CR4","doi-asserted-by":"crossref","unstructured":"Ahmed, E., Jones, M., & Marks, T. K. (2015). An improved deep learning architecture for person re-identification. In CVPR (pp. 3908\u20133916).","DOI":"10.1109\/CVPR.2015.7299016"},{"key":"2284_CR5","doi-asserted-by":"crossref","unstructured":"Bai. Y., Jiao, J., Ce, W., Liu, J., Lou, Y., Feng, X., & Duan, L. Y. (2021a). Person30k: A dual-meta generalization network for person re-identification. In CVPR (pp. 2123\u20132132).","DOI":"10.1109\/CVPR46437.2021.00216"},{"key":"2284_CR6","doi-asserted-by":"crossref","unstructured":"Bai, Z., Wang, Z., Wang, J., Hu, D., & Ding, E. (2021b). Unsupervised multi-source domain adaptation for person re-identification. In CVPR (pp. 12914\u201312923).","DOI":"10.1109\/CVPR46437.2021.01272"},{"key":"2284_CR7","doi-asserted-by":"crossref","unstructured":"Bergamini, L., Porrello, A., Dondona, A. C., Del\u00a0Negro, E., Mattioli, M., D\u2019alterio, N., & Calderara, S. (2018). Multi-views embedding for cattle re-identification. In IEEE SITIS (pp. 184\u2013191).","DOI":"10.1109\/SITIS.2018.00036"},{"key":"2284_CR8","doi-asserted-by":"crossref","unstructured":"Bouma, S., Pawley, M. D., Hupman, K., & Gilman, A. (2018). Individual common dolphin identification via metric embedding learning. In IEEE IVCNZ (pp. 1\u20136).","DOI":"10.1109\/IVCNZ.2018.8634778"},{"key":"2284_CR9","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. NeurIPS, 33, 1877\u20131901.","journal-title":"Language models are few-shot learners. NeurIPS"},{"key":"2284_CR10","doi-asserted-by":"crossref","unstructured":"Bruslund\u00a0Haurum, J., Karpova, A., Pedersen, M., Hein\u00a0Bengtson, S., & Moeslund, T. B. (2020). Re-identification of zebrafish using metric learning. In WACV workshop (pp. 1\u201311).","DOI":"10.1109\/WACVW50321.2020.9096922"},{"key":"2284_CR11","doi-asserted-by":"crossref","unstructured":"Cao, J., Pang, Y., Anwer, R. M., Cholakkal, H., Xie, J., Shah, M., & Khan, F. S. (2022). Pstr: End-to-end one-step person search with transformers. In CVPR (pp. 9458\u20139467).","DOI":"10.1109\/CVPR52688.2022.00924"},{"key":"2284_CR12","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1609\/aaai.v38i1.27801","volume":"38","author":"M Cao","year":"2024","unstructured":"Cao, M., Bai, Y., Zeng, Z., Ye, M., & Zhang, M. (2024). An empirical study of clip for text-based person search. AAAI, 38, 465\u2013473.","journal-title":"AAAI"},{"key":"2284_CR13","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In ICCV (pp. 9650\u20139660).","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2284_CR14","doi-asserted-by":"crossref","unstructured":"Chan, J., Carri\u00f3n, H., M\u00e9gret, R., Agosto-Rivera, J. L., & Giray, T. (2022). Honeybee re-identification in video: New datasets and impact of self-supervision. In VISIGRAPP (5: VISAPP) (pp. 517\u2013525).","DOI":"10.5220\/0010843100003124"},{"issue":"3","key":"2284_CR15","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1007\/s42991-021-00180-9","volume":"102","author":"T Cheeseman","year":"2022","unstructured":"Cheeseman, T., Southerland, K., Park, J., Olio, M., Flynn, K., Calambokidis, J., Jones, L., Garrigue, C., Frisch Jordan, A., Howard, A., et al. (2022). Advanced image recognition: A fully automated, high-accuracy photo-identification matching system for humpback whales. Mammalian Biology, 102(3), 915\u2013929.","journal-title":"Mammalian Biology"},{"key":"2284_CR16","doi-asserted-by":"crossref","unstructured":"Chen, B., Deng, W., & Hu, J. (2019). Mixed high-order attention network for person re-identification. In ICCV (pp 371\u2013381).","DOI":"10.1109\/ICCV.2019.00046"},{"key":"2284_CR17","doi-asserted-by":"crossref","unstructured":"Chen, C., Ye, M., Qi, M., & Du, B. (2022a). Sketch transformer: Asymmetrical disentanglement learning from dynamic synthesis. In ACM MM (pp. 4012\u20134020).","DOI":"10.1145\/3503161.3547993"},{"key":"2284_CR18","first-page":"2352","volume":"31","author":"C Chen","year":"2022","unstructured":"Chen, C., Ye, M., Qi, M., Wu, J., Jiang, J., & Lin, C. W. (2022). Structure-aware positional transformer for visible-infrared person re-identification. IEEE TIP, 31, 2352\u20132364.","journal-title":"IEEE TIP"},{"key":"2284_CR19","doi-asserted-by":"crossref","unstructured":"Chen, C., Ye, M., & Jiang, D. (2023a). Towards modality-agnostic person re-identification with descriptive query. In CVPR (pp. 15128\u201315137).","DOI":"10.1109\/CVPR52729.2023.01452"},{"key":"2284_CR20","doi-asserted-by":"crossref","unstructured":"Chen, H., Lagadec, B., & Bremond, F. (2021a). Ice: Inter-instance contrastive encoding for unsupervised person re-identification. In ICCV (pp. 14960\u201314969).","DOI":"10.1109\/ICCV48922.2021.01469"},{"key":"2284_CR21","doi-asserted-by":"crossref","unstructured":"Chen, S., Ye, M., & Du, B. (2022c). Rotation invariant transformer for recognizing object in UAVs. In ACM MM (pp. 2565\u20132574).","DOI":"10.1145\/3503161.3547799"},{"key":"2284_CR22","doi-asserted-by":"crossref","unstructured":"Chen, W., Xu, X., Jia, J., Luo, H., Wang, Y., Wang, F., Jin, R., & Sun, X. (2023b). Beyond appearance: A semantic controllable self-supervised learning framework for human-centric visual tasks. In CVPR (pp. 15050\u201315061).","DOI":"10.1109\/CVPR52729.2023.01445"},{"key":"2284_CR23","unstructured":"Chen, X., Xu, C., Cao, Q., Xu, J., Zhong, Y., Xu, J., Li, Z., Wang, J., & Gao, S. (2021b). Oh-former: Omni-relational high-order transformer for person re-identification. arXiv preprint arXiv:2109.11159"},{"issue":"2","key":"2284_CR24","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1109\/TPAMI.2017.2666805","volume":"40","author":"YC Chen","year":"2017","unstructured":"Chen, Y. C., Zhu, X., Zheng, W. S., & Lai, J. H. (2017). Person re-identification by camera correlation aware feature augmentation. IEEE TPAMI, 40(2), 392\u2013408.","journal-title":"IEEE TPAMI"},{"key":"2284_CR25","first-page":"3334","volume":"31","author":"D Cheng","year":"2022","unstructured":"Cheng, D., Zhou, J., Wang, N., & Gao, X. (2022). Hybrid dynamic contrast and probability distillation for unsupervised person re-id. IEEE TIP, 31, 3334\u20133346.","journal-title":"IEEE TIP"},{"key":"2284_CR26","doi-asserted-by":"crossref","unstructured":"Cheng, D., Huang, X., Wang, N., He, L., Li, Z., & Gao, X. (2023a). Unsupervised visible-infrared person reid by collaborative learning with neighbor-guided label refinement. In ACM MM (pp. 7085\u20137093).","DOI":"10.1145\/3581783.3612077"},{"key":"2284_CR27","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109270","volume":"137","author":"D Cheng","year":"2023","unstructured":"Cheng, D., Wang, G., Wang, B., Zhang, Q., Han, J., & Zhang, D. (2023). Hybrid routing transformer for zero-shot learning. Pattern Recognition, 137, 109270.","journal-title":"Pattern Recognition"},{"issue":"8","key":"2284_CR28","first-page":"4244","volume":"33","author":"D Cheng","year":"2023","unstructured":"Cheng, D., Wang, G., Wang, N., Zhang, D., Zhang, Q., & Gao, X. (2023). Discriminative and robust attribute alignment for zero-shot learning. IEEE TCSVT, 33(8), 4244\u20134256.","journal-title":"IEEE TCSVT"},{"key":"2284_CR29","doi-asserted-by":"crossref","unstructured":"Cheng, D., Li, Y., Zhang, D., Wang, N., Sun, J., & Gao, X. (2024). Progressive negative enhancing contrastive learning for image dehazing and beyond. In IEEE TMM.","DOI":"10.1109\/TMM.2024.3382493"},{"key":"2284_CR30","doi-asserted-by":"crossref","unstructured":"Cheng, X., Jia, M., Wang, Q., & Zhang, J. (2022b). More is better: Multi-source dynamic parsing attention for occluded person re-identification. In ACM MM (pp. 6840\u20136849).","DOI":"10.1145\/3503161.3547819"},{"key":"2284_CR31","doi-asserted-by":"crossref","unstructured":"Cho, Y., Kim, W. J., Hong, S., & Yoon, S. E. (2022). Part-based pseudo label refinement for unsupervised person re-identification. In CVPR (pp. 7308\u20137318).","DOI":"10.1109\/CVPR52688.2022.00716"},{"key":"2284_CR32","doi-asserted-by":"crossref","unstructured":"Choi, S., Kim, T., Jeong, M., Park, H., & Kim, C. (2021). Meta batch-instance normalization for generalizable person re-identification. In CVPR (pp. 3425\u20133435).","DOI":"10.1109\/CVPR46437.2021.00343"},{"key":"2284_CR33","doi-asserted-by":"crossref","unstructured":"Ci, Y., Wang, Y., Chen, M., Tang, S., Bai, L., Zhu, F., Zhao, R., Yu, F., Qi, D., & Ouyang, W. (2023). Unihcp: A unified model for human-centric perceptions. In CVPR (pp. 17840\u201317852).","DOI":"10.1109\/CVPR52729.2023.01711"},{"key":"2284_CR34","unstructured":"Comandur, B. (2022). Sports re-id: Improving re-identification of players in broadcast videos of team sports. arXiv preprint arXiv:2206.02373"},{"key":"2284_CR35","doi-asserted-by":"crossref","unstructured":"Dai, Y., Liu, J., Sun, Y., Tong, Z., Zhang, C., & Duan, L. Y. (2021). Idm: An intermediate domain module for domain adaptive person re-id. In ICCV (pp. 11864\u201311874).","DOI":"10.1109\/ICCV48922.2021.01165"},{"key":"2284_CR36","unstructured":"Dai, Z., Wang, G., Yuan, W., Zhu, S., & Tan, P. (2022). Cluster contrast for unsupervised person re-identification. In ACCV (pp. 1142\u20131160)."},{"key":"2284_CR37","unstructured":"Dehghani, M., Djolonga, J., Mustafa, B., Padlewski, P., Heek, J., Gilmer, J., Steiner, A. P., Caron, M., Geirhos, R., & Alabdulmohsin, I., et\u00a0al. (2023). Scaling vision transformers to 22 billion parameters. In ICML (pp. 7480\u20137512). PMLR."},{"key":"2284_CR38","doi-asserted-by":"crossref","unstructured":"Deng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., & Jiao, J. (2018). Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification. In CVPR (pp. 994\u20131003).","DOI":"10.1109\/CVPR.2018.00110"},{"key":"2284_CR39","unstructured":"Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"issue":"3","key":"2284_CR40","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1038\/s42256-023-00626-4","volume":"5","author":"N Ding","year":"2023","unstructured":"Ding, N., Qin, Y., Yang, G., Wei, F., Yang, Z., Su, Y., Hu, S., Chen, Y., Chan, C. M., Chen, W., et al. (2023). Parameter-efficient fine-tuning of large-scale pre-trained language models. Nature Machine Intelligence, 5(3), 220\u2013235.","journal-title":"Nature Machine Intelligence"},{"key":"2284_CR41","unstructured":"Ding, Z., Ding, C., Shao, Z., & Tao, D. (2021). Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv preprint arXiv:2107.12666"},{"key":"2284_CR42","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S., et\u00a0al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR."},{"key":"2284_CR43","doi-asserted-by":"crossref","unstructured":"Fan, L., Li, T., Fang, R., Hristov, R., Yuan, Y., & Katabi, D. (2020). Learning longterm representations for person re-identification using radio signals. In CVPR (pp. 10699\u201310709).","DOI":"10.1109\/CVPR42600.2020.01071"},{"key":"2284_CR44","doi-asserted-by":"crossref","first-page":"4477","DOI":"10.1609\/aaai.v36i4.20370","volume":"36","author":"A Farooq","year":"2022","unstructured":"Farooq, A., Awais, M., Kittler, J., & Khalid, S. S. (2022). Axm-net: Implicit cross-modal feature alignment for person re-identification. AAAI, 36, 4477\u20134485.","journal-title":"AAAI"},{"key":"2284_CR45","doi-asserted-by":"crossref","unstructured":"Feng, Y., Yu, J., Chen, F., Ji, Y., Wu, F., Liu, S., & Jing, X. Y. (2022). Visible-infrared person re-identification via cross-modality interaction transformer. In IEEE TMM.","DOI":"10.1109\/TMM.2022.3224663"},{"key":"2284_CR46","doi-asserted-by":"crossref","unstructured":"Ferdous, S. N., Li, X., & Lyu, S. (2022). Uncertainty aware multitask pyramid vision transformer for uav-based object re-identification. In ICIP (pp. 2381\u20132385). IEEE.","DOI":"10.1109\/ICIP46576.2022.9898013"},{"key":"2284_CR47","doi-asserted-by":"crossref","unstructured":"Fu, D., Chen, D., Bao, J., Yang, H., Yuan, L., Zhang, L., Li, H., & Chen, D. (2021). Unsupervised pre-training for person re-identification. In CVPR (pp. 14750\u201314759).","DOI":"10.1109\/CVPR46437.2021.01451"},{"key":"2284_CR48","unstructured":"Gao, J., Burghardt, T., Andrew, W., Dowsey, A. W., & Campbell, N. W. (2021). Towards self-supervision for video identification of individual holstein-friesian cattle: The cows2021 dataset. arXiv preprint arXiv:2105.01938"},{"key":"2284_CR49","first-page":"11309","volume":"33","author":"Y Ge","year":"2020","unstructured":"Ge, Y., Zhu, F., Chen, D., Zhao, R., et al. (2020). Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. NeurIPS, 33, 11309\u201311321.","journal-title":"NeurIPS"},{"key":"2284_CR50","first-page":"1","volume":"3","author":"D Gray","year":"2007","unstructured":"Gray, D., Brennan, S., & Tao, H. (2007). Evaluating appearance models for recognition, reacquisition, and tracking. PETS, 3, 1\u20137.","journal-title":"PETS"},{"key":"2284_CR51","unstructured":"Gu, J., Luo, H., Wang, K., Jiang, W., You, Y., & Zhao, J. (2023). Color prompting for data-free continual unsupervised domain adaptive person re-identification. arXiv preprint arXiv:2308.10716"},{"issue":"9","key":"2284_CR52","first-page":"4328","volume":"28","author":"H Guo","year":"2019","unstructured":"Guo, H., Zhu, K., Tang, M., & Wang, J. (2019). Two-level attention network with multi-grain ranking loss for vehicle re-identification. IEEE TIP, 28(9), 4328\u20134338.","journal-title":"IEEE TIP"},{"key":"2284_CR53","doi-asserted-by":"crossref","unstructured":"Guo, P., Liu, H., Wu, J., Wang, G., & Wang, T. (2023). Semantic-aware consistency network for cloth-changing person re-identification. arXiv preprint arXiv:2308.14113","DOI":"10.1145\/3581783.3612416"},{"issue":"1","key":"2284_CR54","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han, K., Wang, Y., Chen, H., Chen, X., Guo, J., Liu, Z., Tang, Y., Xiao, A., Xu, C., Xu, Y., et al. (2022). A survey on vision transformer. IEEE TPAMI, 45(1), 87\u2013110.","journal-title":"IEEE TPAMI"},{"key":"2284_CR55","unstructured":"Han, X., He, S., Zhang, L., & Xiang, T. (2021). Text-based person search with limited data. arXiv:2110.10807"},{"key":"2284_CR56","doi-asserted-by":"crossref","unstructured":"He, B., Li, J., Zhao, Y., & Tian, Y. (2019). Part-regularized near-duplicate vehicle re-identification. In CVPR (pp. 3997\u20134005).","DOI":"10.1109\/CVPR.2019.00412"},{"key":"2284_CR57","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2284_CR58","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In CVPR (pp. 16000\u201316009).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2284_CR59","doi-asserted-by":"crossref","unstructured":"He, S., Luo, H., Wang, P., Wang, F., Li, H., & Jiang, W. (2021a). Transreid: Transformer-based object re-identification. In ICCV (pp. 15013\u201315022).","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"2284_CR60","doi-asserted-by":"crossref","unstructured":"He, S., Chen, W., Wang, K., Luo, H., Wang, F., Jiang, W., & Ding, H. (2023a). Region generation and assessment network for occluded person re-identification. In IEEE TIFS.","DOI":"10.1109\/TIFS.2023.3318956"},{"key":"2284_CR61","first-page":"163","volume":"33","author":"S He","year":"2023","unstructured":"He, S., Luo, H., Jiang, W., Jiang, X., & Ding, H. (2023). Vgsg: Vision-guided semantic-group network for text-based person search. IEEE TIP, 33, 163\u2013176.","journal-title":"IEEE TIP"},{"key":"2284_CR62","doi-asserted-by":"crossref","unstructured":"He, T., Jin, X., Shen, X., Huang, J., Chen, Z., Hua, X. S. (2021b). Dense interaction learning for video-based person re-identification. In ICCV (pp. 1490\u20131501).","DOI":"10.1109\/ICCV48922.2021.00152"},{"key":"2284_CR63","doi-asserted-by":"crossref","unstructured":"He, T., Shen, X., Huang, J., Chen, Z., & Hua, X. S. (2021c). Partial person re-identification with part-part correspondence learning. In CVPR (pp. 9105\u20139115).","DOI":"10.1109\/CVPR46437.2021.00899"},{"key":"2284_CR64","doi-asserted-by":"crossref","unstructured":"He, W., Deng, Y., Tang, S., Chen, Q., Xie, Q., Wang, Y., Bai, L., Zhu, F., Zhao, R., & Ouyang, W., et\u00a0al. (2024). Instruct-reid: A multi-purpose person re-identification task with instructions. In CVPR (pp. 17521\u201317531).","DOI":"10.1109\/CVPR52733.2024.01659"},{"key":"2284_CR65","unstructured":"Hermans, A., Beyer, L., & Leibe, B. (2017). In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737"},{"key":"2284_CR66","doi-asserted-by":"crossref","unstructured":"Hong, P., Wu, T., Wu, A., Han, X., & Zheng, W. S. (2021). Fine-grained shape-appearance mutual learning for cloth-changing person re-identification. In CVPR (pp. 10513\u201310522).","DOI":"10.1109\/CVPR46437.2021.01037"},{"key":"2284_CR67","unstructured":"Howard, A., Ken, I., Southerland\u00a0Holbrook. R., & Cheeseman, T. (2022). Happywhale - whale and dolphin identification. https:\/\/kaggle.com\/competitions\/happy-whale-and-dolphin"},{"key":"2284_CR68","first-page":"1294","volume":"25","author":"M Jia","year":"2022","unstructured":"Jia, M., Cheng, X., Lu, S., & Zhang, J. (2022). Learning disentangled representation implicitly via transformer for occluded person re-identification. IEEE TMM, 25, 1294\u20131305.","journal-title":"IEEE TMM"},{"key":"2284_CR69","first-page":"4227","volume":"31","author":"X Jia","year":"2022","unstructured":"Jia, X., Zhong, X., Ye, M., Liu, W., & Huang, W. (2022). Complementary data augmentation for cloth-changing person re-identification. IEEE TIP, 31, 4227\u20134239.","journal-title":"IEEE TIP"},{"key":"2284_CR70","doi-asserted-by":"crossref","unstructured":"Jiang, D., & Ye, M. (2023). Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval. In CVPR (pp. 2787\u20132797).","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"2284_CR71","doi-asserted-by":"crossref","unstructured":"Jiang, K., Zhang, T., Liu, X., Qian, B., Zhang, Y., & Wu, F. (2022). Cross-modality transformer for visible-infrared person re-identification. In ECCV (pp. 480\u2013496). Springer.","DOI":"10.1007\/978-3-031-19781-9_28"},{"key":"2284_CR72","unstructured":"Jiao, B., Liu, L., Gao, L., Wu, R., Lin, G., Wang, P., & Zhang, Y. (2023). Toward re-identifying any animal. In NeurIPS."},{"key":"2284_CR73","doi-asserted-by":"crossref","unstructured":"Jin, X., Lan, C., Zeng, W., Chen, Z., & Zhang, L. (2020). Style normalization and restitution for generalizable person re-identification. In CVPR (pp. 3143\u20133152).","DOI":"10.1109\/CVPR42600.2020.00321"},{"key":"2284_CR74","doi-asserted-by":"crossref","unstructured":"Jin, X., He, T., Zheng, K., Yin, Z., Shen, X., Huang, Z., Feng, R., Huang, J., Chen, Z., & Hua, X. S. (2022). Cloth-changing person re-identification from a single image with gait prediction and regularization. In CVPR (pp. 14278\u201314287).","DOI":"10.1109\/CVPR52688.2022.01388"},{"key":"2284_CR75","doi-asserted-by":"crossref","unstructured":"Kalayeh, M. M., Basaran, E., G\u00f6kmen, M., Kamasak, M. E., & Shah, M. (2018). Human semantic parsing for person re-identification. In CVPR (pp. 1062\u20131071).","DOI":"10.1109\/CVPR.2018.00117"},{"key":"2284_CR76","first-page":"50","volume":"182","author":"SD Khan","year":"2019","unstructured":"Khan, S. D., & Ullah, H. (2019). A survey of advances in vision-based vehicle re-identification. CVIU, 182, 50\u201363.","journal-title":"CVIU"},{"key":"2284_CR77","doi-asserted-by":"crossref","unstructured":"Khorramshahi, P., Kumar, A., Peri, N., Rambhatla, S. S., Chen, J. C., & Chellappa, R. (2019). A dual-path model with adaptive attention for vehicle re-identification. In ICCV (pp. 6132\u20136141).","DOI":"10.1109\/ICCV.2019.00623"},{"key":"2284_CR78","unstructured":"Koch, G., Zemel, R., & Salakhutdinov, R., et\u00a0al. (2015). Siamese neural networks for one-shot image recognition. In ICML workshop (vol.\u00a02). Lille."},{"key":"2284_CR79","doi-asserted-by":"crossref","first-page":"25","DOI":"10.4236\/gep.2018.65003","volume":"6","author":"DA Konovalov","year":"2018","unstructured":"Konovalov, D. A., Hillcoat, S., Williams, G., Birtles, R. A., Gardiner, N., & Curnock, M. I. (2018). Individual minke whale recognition using deep learning convolutional neural networks. Journal of Geoscience and Environment Protection, 6, 25\u201336.","journal-title":"Journal of Geoscience and Environment Protection"},{"key":"2284_CR80","doi-asserted-by":"crossref","unstructured":"Korschens, M., & Denzler, J. (2019). Elpephants: A fine-grained dataset for elephant re-identification. In ICCV workshop.","DOI":"10.1109\/ICCVW.2019.00035"},{"key":"2284_CR81","doi-asserted-by":"crossref","unstructured":"Kumar, S., Yaghoubi, E., Das, A., Harish, B., & Proen\u00e7a, H. (2020). The p-destre: A fully annotated dataset for pedestrian detection, tracking, re-identification and search from aerial devices. arXiv preprint arXiv:2004.02782","DOI":"10.1109\/TIFS.2020.3040881"},{"key":"2284_CR82","doi-asserted-by":"crossref","unstructured":"Kuncheva, L. I., Williams, F., Hennessey, S. L., & Rodr\u00edguez, J. J. (2022). A benchmark database for animal re-identification and tracking. In IEEE IPAS (pp. 1\u20136). IEEE.","DOI":"10.1109\/IPAS55744.2022.10052988"},{"key":"2284_CR83","doi-asserted-by":"crossref","unstructured":"Lai, S., Chai, Z., & Wei, X. (2021). Transformer meets part model: Adaptive part division for person re-identification. In ICCV (pp. 4150\u20134157).","DOI":"10.1109\/ICCVW54120.2021.00461"},{"key":"2284_CR84","doi-asserted-by":"crossref","unstructured":"Lee, K. W., Jawade, B., Mohan, D., Setlur, S., & Govindaraju, V. (2022). Attribute de-biased vision transformer (ad-vit) for long-term person re-identification. In IEEE AVSS (pp. 1\u20138) . IEEE.","DOI":"10.1109\/AVSS56176.2022.9959509"},{"key":"2284_CR85","first-page":"11345","volume":"34","author":"H Li","year":"2020","unstructured":"Li, H., Li, C., Zhu, X., Zheng, A., & Luo, B. (2020). Multi-spectral vehicle re-identification: A challenge. AAAI, 34, 11345\u201311353.","journal-title":"Multi-spectral vehicle re-identification: A challenge. AAAI"},{"key":"2284_CR86","doi-asserted-by":"crossref","unstructured":"Li, H., Wu, G., & Zheng, W. S. (2021a). Combined depth space based architecture search for person re-identification. In CVPR (pp. 6729\u20136738).","DOI":"10.1109\/CVPR46437.2021.00666"},{"key":"2284_CR87","doi-asserted-by":"crossref","unstructured":"Li, H., Ye, M., & Du, B. (2021b). Weperson: Learning a generalized re-identification model from all-weather virtual data. In ACM MM (pp. 3115\u20133123).","DOI":"10.1145\/3474085.3475455"},{"issue":"10","key":"2284_CR88","first-page":"19557","volume":"23","author":"H Li","year":"2022","unstructured":"Li, H., Li, C., Zheng, A., Tang, J., & Luo, B. (2022). Mskat: Multi-scale knowledge-aware transformer for vehicle re-identification. IEEE TITS, 23(10), 19557\u201319568.","journal-title":"IEEE TITS"},{"key":"2284_CR89","doi-asserted-by":"crossref","unstructured":"Li, H., Ye, M., Wang, C., & Du, B. (2022b). Pyramidal transformer with conv-patchify for person re-identification. In ACM MM (pp. 7317\u20137326).","DOI":"10.1145\/3503161.3548770"},{"key":"2284_CR90","doi-asserted-by":"crossref","unstructured":"Li, H., Ye, M., Zhang, M., Du, B. (2024a). All in one framework for multimodal re-identification in the wild. In CVPR (pp. 17459\u201317469).","DOI":"10.1109\/CVPR52733.2024.01653"},{"issue":"7","key":"2284_CR91","first-page":"1770","volume":"42","author":"M Li","year":"2019","unstructured":"Li, M., Zhu, X., & Gong, S. (2019). Unsupervised tracklet person re-identification. IEEE TPAMI, 42(7), 1770\u20131782.","journal-title":"Unsupervised tracklet person re-identification. IEEE TPAMI"},{"key":"2284_CR92","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Zhou, B., Yue, D., & Wang, X. (2017). Person search with natural language description. In CVPR (pp. 1970\u20131979).","DOI":"10.1109\/CVPR.2017.551"},{"key":"2284_CR93","doi-asserted-by":"crossref","unstructured":"Li, S., Li, J., Tang, H., Qian, R., & Lin, W. (2019b). Atrw: A benchmark for amur tiger re-identification in the wild. arXiv preprint arXiv:1906.05586","DOI":"10.1145\/3394171.3413569"},{"issue":"11","key":"2284_CR94","volume":"16","author":"S Li","year":"2021","unstructured":"Li, S., Fu, L., Sun, Y., Mu, Y., Chen, L., Li, J., & Gong, H. (2021). Individual dairy cow identification based on lightweight convolutional neural network. Plos one, 16(11), e0260510.","journal-title":"Plos one"},{"key":"2284_CR95","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.1609\/aaai.v37i1.25225","volume":"37","author":"S Li","year":"2023","unstructured":"Li, S., Sun, L., & Li, Q. (2023). Clip-reid: Exploiting vision-language model for image re-identification without concrete text labels. AAAI, 37, 1405\u20131413.","journal-title":"AAAI"},{"key":"2284_CR96","doi-asserted-by":"crossref","unstructured":"Li, T., Liu, J., Zhang, W., Ni, Y., Wang, W., & Li, Z. (2021d). Uav-human: A large benchmark for human behavior understanding with unmanned aerial vehicles. In CVPR (pp. 16266\u201316275).","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"2284_CR97","doi-asserted-by":"crossref","unstructured":"Li, W., Zhao, R., Xiao, T., & Wang, X. (2014). Deepreid: Deep filter pairing neural network for person re-identification. In CVPR (pp. 152\u2013159).","DOI":"10.1109\/CVPR.2014.27"},{"key":"2284_CR98","doi-asserted-by":"crossref","unstructured":"Li, W., Zhu, X., & Gong, S. (2018). Harmonious attention network for person re-identification. In CVPR (pp. 2285\u20132294).","DOI":"10.1109\/CVPR.2018.00243"},{"key":"2284_CR99","doi-asserted-by":"crossref","unstructured":"Li, W., Zou, C., Wang, M., Xu, F., Zhao, J., Zheng, R., Cheng, Y., & Chu, W. (2023b). Dc-former: Diverse and compact transformer for person re-identification. arXiv preprint arXiv:2302.14335","DOI":"10.1609\/aaai.v37i2.25226"},{"key":"2284_CR100","doi-asserted-by":"crossref","unstructured":"Li, Y., He, J., Zhang, T., Liu, X., Zhang, Y., & Wu, F. (2021e). Diverse part discovery: Occluded person re-identification with part-aware transformer. In CVPR (pp. 2898\u20132907).","DOI":"10.1109\/CVPR46437.2021.00292"},{"key":"2284_CR101","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, Y., Zhang, H., Zhao, C., Wei, Z., & Miao, D. (2024b). Occlusion-aware transformer with second-order attention for person re-identification. IEEE TIP","DOI":"10.1109\/TIP.2024.3393360"},{"key":"2284_CR102","doi-asserted-by":"crossref","unstructured":"Liang, T., Jin, Y., Liu, W., & Li, Y. (2023). Cross-modality transformer with modality mining for visible-infrared person re-identification. IEEE TMM","DOI":"10.2139\/ssrn.4944583"},{"key":"2284_CR103","first-page":"1992","volume":"34","author":"S Liao","year":"2021","unstructured":"Liao, S., & Shao, L. (2021). Transmatcher: Deep image matching through transformers for generalizable person re-identification. NeurIPS, 34, 1992\u20132003.","journal-title":"NeurIPS"},{"key":"2284_CR104","doi-asserted-by":"crossref","unstructured":"Liao, S., Hu, Y., Zhu, X., & Li, S. Z. (2015). Person re-identification by local maximal occurrence representation and metric learning. In CVPR (pp. 2197\u20132206).","DOI":"10.1109\/CVPR.2015.7298832"},{"issue":"3","key":"2284_CR105","doi-asserted-by":"crossref","first-page":"1478","DOI":"10.1109\/TCYB.2019.2917713","volume":"51","author":"W Lin","year":"2019","unstructured":"Lin, W., Li, Y., Xiao, H., See, J., Zou, J., Xiong, H., Wang, J., & Mei, T. (2019). Group reidentification with multigrained matching and integration. IEEE transactions on cybernetics, 51(3), 1478\u20131492.","journal-title":"IEEE transactions on cybernetics"},{"key":"2284_CR106","doi-asserted-by":"crossref","first-page":"8738","DOI":"10.1609\/aaai.v33i01.33018738","volume":"33","author":"Y Lin","year":"2019","unstructured":"Lin, Y., Dong, X., Zheng, L., Yan, Y., & Yang, Y. (2019). A bottom-up clustering approach to unsupervised person re-identification. AAAI, 33, 8738\u20138745.","journal-title":"AAAI"},{"key":"2284_CR107","doi-asserted-by":"crossref","unstructured":"Lin, Y., Xie, L., Wu, Y., Yan, C., & Tian, Q. (2020). Unsupervised person re-identification via softened similarity learning. In CVPR (pp. 3390\u20133399).","DOI":"10.1109\/CVPR42600.2020.00345"},{"key":"2284_CR108","doi-asserted-by":"crossref","unstructured":"Liu, F., Ye, M., & Du, B. (2023a). Dual level adaptive weighting for cloth-changing person re-identification. IEEE TIP","DOI":"10.1109\/TIP.2023.3310307"},{"issue":"10","key":"2284_CR109","doi-asserted-by":"crossref","first-page":"2788","DOI":"10.1109\/TCSVT.2017.2715499","volume":"28","author":"H Liu","year":"2017","unstructured":"Liu, H., Jie, Z., Jayashree, K., Qi, M., Jiang, J., Yan, S., & Feng, J. (2017). Video-based person re-identification with accumulative motion context. IEEE Transactions on Circuits and Systems for Video Technology, 28(10), 2788\u20132802.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2284_CR110","doi-asserted-by":"crossref","unstructured":"Liu, X., Liu, W., Ma, H., & Fu, H. (2016a). Large-scale vehicle re-identification in urban surveillance videos. In ICME (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICME.2016.7553002"},{"key":"2284_CR111","doi-asserted-by":"crossref","unstructured":"Liu, X., Liu, W., Mei, T., & Ma, H. (2016b). A deep learning-based approach to progressive vehicle re-identification for urban surveillance. In ECCV (pp. 869\u2013884). Springer.","DOI":"10.1007\/978-3-319-46475-6_53"},{"key":"2284_CR112","unstructured":"Liu, X., Zhang, P., Yu, C., Lu, H., Qian, X., & Yang, X. (2021a). A video is worth three views: Trigeminal transformers for video-based person re-identification. arXiv preprint arXiv:2104.01745"},{"key":"2284_CR113","doi-asserted-by":"crossref","unstructured":"Liu, X., Yu, C., Zhang, P., & Lu, H. (2023b). Deeply coupled convolution\u2013transformer with spatial\u2013temporal complementary learning for video-based person re-identification. In IEEE TNNLS.","DOI":"10.1109\/TNNLS.2023.3271353"},{"key":"2284_CR114","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021b). Swin transformer: Hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2284_CR115","doi-asserted-by":"crossref","unstructured":"Lou, Y., Bai, Y., Liu, J., Wang, S., & Duan, L. (2019). Veri-wild: A large dataset and a new method for vehicle re-identification in the wild. In CVPR (pp. 3235\u20133243).","DOI":"10.1109\/CVPR.2019.00335"},{"issue":"10","key":"2284_CR116","first-page":"2597","volume":"22","author":"H Luo","year":"2019","unstructured":"Luo, H., Jiang, W., Gu, Y., Liu, F., Liao, X., Lai, S., & Gu, J. (2019). A strong baseline and batch normalization neck for deep person re-identification. IEEE TMM, 22(10), 2597\u20132609.","journal-title":"IEEE TMM"},{"key":"2284_CR117","unstructured":"Luo, H., Wang, P., Xu, Y., Ding, F., Zhou, Y., Wang, F., Li, H., & Jin, R. (2021). Self-supervised pre-training for transformer-based person re-identification. arXiv preprint arXiv:2111.12084"},{"issue":"7","key":"2284_CR118","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/34.192463","volume":"11","author":"SG Mallat","year":"1989","unstructured":"Mallat, S. G. (1989). A theory for multiresolution signal decomposition: The wavelet representation. IEEE TPAMI, 11(7), 674\u2013693.","journal-title":"IEEE TPAMI"},{"key":"2284_CR119","doi-asserted-by":"crossref","unstructured":"Mao, J., Yao, Y., Sun, Z., Huang, X., Shen, F., & Shen, H. T. (2023). Attention map guided transformer pruning for occluded person re-identification on edge device. In IEEE TMM.","DOI":"10.1109\/TMM.2023.3265159"},{"key":"2284_CR120","doi-asserted-by":"crossref","unstructured":"McLaughlin, N., Del\u00a0Rincon, J. M., & Miller, P. (2016). Recurrent convolutional network for video-based person re-identification. In CVPR (pp. 1325\u20131334).","DOI":"10.1109\/CVPR.2016.148"},{"key":"2284_CR121","doi-asserted-by":"crossref","unstructured":"Meng, D., Li, L., Liu, X., Li, Y., Yang, S., Zha, Z. J., Gao, X., Wang, S., Huang, Q. (2020). Parsing-based view-aware embedding network for vehicle re-identification. In CVPR (pp. 7103\u20137112).","DOI":"10.1109\/CVPR42600.2020.00713"},{"key":"2284_CR122","doi-asserted-by":"crossref","unstructured":"Miao, J., Wu, Y., Liu, P., Ding, Y., & Yang, Y. (2019). Pose-guided feature alignment for occluded person re-identification. In ICCV (pp. 542\u2013551).","DOI":"10.1109\/ICCV.2019.00063"},{"key":"2284_CR123","doi-asserted-by":"crossref","unstructured":"Moskvyak, O., Maire, F., Dayoub, F., & Baktashmotlagh, M. (2020). Learning landmark guided embeddings for animal re-identification. In WACV workshop (pp. 12\u201319).","DOI":"10.1109\/WACVW50321.2020.9096932"},{"key":"2284_CR124","doi-asserted-by":"crossref","unstructured":"Moskvyak, O., Maire, F., Dayoub, F., Armstrong, A. O., & Baktashmotlagh, M. (2021). Robust re-identification of manta rays from natural markings by learning pose invariant embeddings. In DICTA (pp. 1\u20138). IEEE.","DOI":"10.1109\/DICTA52665.2021.9647359"},{"key":"2284_CR125","unstructured":"Naseer, M., Ranasinghe, K., Khan, S., Hayat, M., Khan, F. S., & Yang, M. H. (2021). Intriguing properties of vision transformers. arXiv preprint arXiv:2105.10497"},{"key":"2284_CR126","doi-asserted-by":"crossref","unstructured":"Nepovinnykh, E., Eerola, T., & Kalviainen, H. (2020). Siamese network based pelage pattern matching for ringed seal re-identification. In WACV workshop (pp. 25\u201334).","DOI":"10.1109\/WACVW50321.2020.9096935"},{"issue":"19","key":"2284_CR127","doi-asserted-by":"crossref","first-page":"7602","DOI":"10.3390\/s22197602","volume":"22","author":"E Nepovinnykh","year":"2022","unstructured":"Nepovinnykh, E., Eerola, T., Biard, V., Mutka, P., Niemi, M., Kunnasranta, M., & K\u00e4lvi\u00e4inen, H. (2022). Sealid: Saimaa ringed seal re-identification dataset. Sensors, 22(19), 7602.","journal-title":"Sensors"},{"issue":"3","key":"2284_CR128","doi-asserted-by":"crossref","first-page":"605","DOI":"10.3390\/s17030605","volume":"17","author":"DT Nguyen","year":"2017","unstructured":"Nguyen, D. T., Hong, H. G., Kim, K. W., & Park, K. R. (2017). Person recognition system based on a combination of body images from visible light and thermal cameras. Sensors, 17(3), 605.","journal-title":"Sensors"},{"key":"2284_CR129","doi-asserted-by":"crossref","unstructured":"Ni, H., Song, J., Luo, X., Zheng, F., Li, W., & Shen, H. T. (2022). Meta distribution alignment for generalizable person re-identification. In CVPR (pp. 2487\u20132496).","DOI":"10.1109\/CVPR52688.2022.00252"},{"key":"2284_CR130","doi-asserted-by":"crossref","unstructured":"Ni, H., Li, Y., Gao, L., Shen, H. T., & Song, J. (2023). Part-aware transformer for generalizable person re-identification. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 11280\u201311289).","DOI":"10.1109\/ICCV51070.2023.01036"},{"key":"2284_CR131","doi-asserted-by":"crossref","unstructured":"Niu, K., Huang, Y., Ouyang, W., & Wang, L. (2020). Improving description-based person re-identification by multi-granularity image-text alignments. In IEEE TIP (pp. 5542\u20135556).","DOI":"10.1109\/TIP.2020.2984883"},{"key":"2284_CR132","doi-asserted-by":"crossref","unstructured":"Organisciak, D., Poyser, M., Alsehaim, A., Hu, S., Isaac-Medina, B. K., Breckon, T. P., Shum, H. P. (2021). Uav-reid: A benchmark on unmanned aerial vehicle re-identification in video imagery. arXiv preprint arXiv:2104.06219","DOI":"10.5220\/0010836600003124"},{"key":"2284_CR133","doi-asserted-by":"crossref","unstructured":"Pang, L., Wang, Y., Song, Y. Z., Huang, T., Tian, Y. (2018). Cross-domain adversarial feature learning for sketch re-identification. In ACM MM (pp. 609\u2013617).","DOI":"10.1145\/3240508.3240606"},{"key":"2284_CR134","unstructured":"Papafitsoros, K., Adam, L., \u010cerm\u00e1k, V., & Picek, L. (2022). Seaturtleid: A novel long-span dataset highlighting the importance of timestamps in wildlife re-identification. arXiv preprint arXiv:2211.10307"},{"key":"2284_CR135","unstructured":"Parham, J., Crall, J., Stewart, C., Berger-Wolf, T., Rubenstein, D. I. (2017). Animal population censusing at scale with citizen science and photographic identification. In AAAI."},{"key":"2284_CR136","first-page":"11839","volume":"34","author":"H Park","year":"2020","unstructured":"Park, H., & Ham, B. (2020). Relation network for person re-identification. AAAI, 34, 11839\u201311847.","journal-title":"Relation network for person re-identification. AAAI"},{"key":"2284_CR137","doi-asserted-by":"crossref","unstructured":"Porrello, A., Bergamini, L., & Calderara, S. (2020). Robust re-identification by multiple views knowledge distillation. In ECCV (pp. 93\u2013110). Springer.","DOI":"10.1007\/978-3-030-58607-2_6"},{"key":"2284_CR138","doi-asserted-by":"crossref","unstructured":"Pu, N., Zhong, Z., Sebe, N., Lew, M. S. (2023). A memorizing and generalizing framework for lifelong person re-identification. In IEEE TPAMI","DOI":"10.1109\/TPAMI.2023.3297058"},{"key":"2284_CR139","doi-asserted-by":"crossref","unstructured":"Qian, W., Luo, H., Peng, S., Wang, F., Chen, C., & Li, H. (2022). Unstructured feature decoupling for vehicle re-identification. In ECCV (pp. 336\u2013353).","DOI":"10.1007\/978-3-031-19781-9_20"},{"key":"2284_CR140","doi-asserted-by":"crossref","unstructured":"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 ACCV.","DOI":"10.1007\/978-3-030-69535-4_5"},{"key":"2284_CR141","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., & Clark, J., et\u00a0al. (2021). Learning transferable visual models from natural language supervision. In ICML (pp. 8748\u20138763). PMLR."},{"key":"2284_CR142","doi-asserted-by":"crossref","unstructured":"Rao, H., & Miao, C. (2023). Transg: Transformer-based skeleton graph prototype contrastive learning with structure-trajectory prompted reconstruction for person re-identification. In CVPR (pp. 22118\u201322128).","DOI":"10.1109\/CVPR52729.2023.02118"},{"issue":"10","key":"2284_CR143","doi-asserted-by":"crossref","first-page":"6649","DOI":"10.1109\/TPAMI.2021.3092833","volume":"44","author":"H Rao","year":"2021","unstructured":"Rao, H., Wang, S., Hu, X., Tan, M., Guo, Y., Cheng, J., Liu, X., & Hu, B. (2021). A self-supervised gait encoding approach with locality-awareness for 3d skeleton based person re-identification. IEEE TPAMI, 44(10), 6649\u20136666.","journal-title":"IEEE TPAMI"},{"issue":"1","key":"2284_CR144","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1007\/s11263-023-01864-0","volume":"132","author":"H Rao","year":"2024","unstructured":"Rao, H., Leung, C., & Miao, C. (2024). Hierarchical skeleton meta-prototype contrastive learning with hard skeleton mining for unsupervised person re-identification. IJCV, 132(1), 238\u2013260.","journal-title":"IJCV"},{"key":"2284_CR145","doi-asserted-by":"crossref","unstructured":"Sarafianos, N., Xu, X., & Kakadiaris, I. A. (2019). Adversarial representation learning for text-to-image matching. In ICCV (pp. 5814\u20135824).","DOI":"10.1109\/ICCV.2019.00591"},{"issue":"4","key":"2284_CR146","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1111\/2041-210X.13133","volume":"10","author":"S Schneider","year":"2019","unstructured":"Schneider, S., Taylor, G. W., Linquist, S., & Kremer, S. C. (2019). Past, present and future approaches using computer vision for animal re-identification from camera trap data. Methods in Ecology and Evolution, 10(4), 461\u2013470.","journal-title":"Methods in Ecology and Evolution"},{"key":"2284_CR147","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhang, X., Fang, M., Lin, Z., Wang, J., & Ding, C. (2022). Learning granularity-unified representations for text-to-image person re-identification. In ACM MM (pp. 5566\u20135574).","DOI":"10.1145\/3503161.3548028"},{"key":"2284_CR148","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhang, X., Ding, C., Wang, J., & Wang, J. (2023). Unified pre-training with pseudo texts for text-to-image person re-identification. In ICCV (pp. 11174\u201311184).","DOI":"10.1109\/ICCV51070.2023.01026"},{"key":"2284_CR149","first-page":"1039","volume":"32","author":"F Shen","year":"2023","unstructured":"Shen, F., Xie, Y., Zhu, J., Zhu, X., & Zeng, H. (2023). Git: Graph interactive transformer for vehicle re-identification. IEEE TIP, 32, 1039\u20131051.","journal-title":"IEEE TIP"},{"key":"2284_CR150","doi-asserted-by":"crossref","unstructured":"Shen, L., He, T., Guo, Y., & Ding, G. (2023b). X-reid: Cross-instance transformer for identity-level person re-identification. arXiv preprint arXiv:2302.02075","DOI":"10.1109\/ICME57554.2024.10687457"},{"key":"2284_CR151","doi-asserted-by":"crossref","unstructured":"Shu, X., Wen, W., Wu, H., Chen, K., Song, Y., Qiao, R., Ren, B., & Wang, X. (2022). See finer, see more: Implicit modality alignment for text-based person retrieval. In ECCV (pp. 624\u2013641). Springer.","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"2284_CR152","doi-asserted-by":"crossref","unstructured":"Song, G., Leng, B., Liu, Y., Hetang, C., & Cai, S. (2018). Region-based quality estimation network for large-scale person re-identification. In AAAI (vol.\u00a032).","DOI":"10.1609\/aaai.v32i1.12305"},{"key":"2284_CR153","doi-asserted-by":"crossref","unstructured":"Su, C., Li, J., Zhang, S., Xing, J., Gao, W., & Tian, Q. (2017). Pose-driven deep convolutional model for person re-identification. In ICCV (pp. 3960\u20133969).","DOI":"10.1109\/ICCV.2017.427"},{"key":"2284_CR154","doi-asserted-by":"crossref","unstructured":"Suh, Y., Wang, J., Tang, S., Mei, T., & Lee, K. M. (2018). Part-aligned bilinear representations for person re-identification. In ECCV (pp. 402\u2013419).","DOI":"10.1007\/978-3-030-01264-9_25"},{"issue":"3","key":"2284_CR155","first-page":"155","volume":"5","author":"CC Sun","year":"2004","unstructured":"Sun, C. C., Arr, G. S., Ramachandran, R. P., & Ritchie, S. G. (2004). Vehicle reidentification using multidetector fusion. IEEE TITS, 5(3), 155\u2013164.","journal-title":"IEEE TITS"},{"key":"2284_CR156","doi-asserted-by":"crossref","unstructured":"Sun, X., & Zheng, L. (2019). Dissecting person re-identification from the viewpoint of viewpoint. In CVPR (pp. 608\u2013617).","DOI":"10.1109\/CVPR.2019.00070"},{"key":"2284_CR157","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zheng, L., Yang, Y., Tian, Q., & Wang, S. (2018). Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline). In ECCV (pp. 480\u2013496)","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"2284_CR158","doi-asserted-by":"crossref","unstructured":"Tan, B., Xu, L., Qiu, Z., Wu, Q., & Meng, F. (2023). Mfat: A multi-level feature aggregated transformer for person re-identification. In ICASSP (pp. 1\u20135). IEEE.","DOI":"10.1109\/ICASSP49357.2023.10095095"},{"key":"2284_CR159","doi-asserted-by":"crossref","unstructured":"Tan, W., Ding, C., Jiang, J., Wang, F., Zhan, Y., & Tao, D. (2024). Harnessing the power of mllms for transferable text-to-image person reid. In CVPR (pp. 17127\u201317137).","DOI":"10.1109\/CVPR52733.2024.01621"},{"key":"2284_CR160","doi-asserted-by":"crossref","unstructured":"Tang, S., Chen, C., Xie, Q., Chen, M., Wang, Y., Ci, Y., Bai, L., Zhu, F., Yang, H., & Yi, L., et\u00a0al. (2023). Humanbench: Towards general human-centric perception with projector assisted pretraining. In CVPR (pp. 21970\u201321982).","DOI":"10.1109\/CVPR52729.2023.02104"},{"key":"2284_CR161","doi-asserted-by":"crossref","unstructured":"Tang, Z., Naphade, M., Liu, M. Y., Yang, X., Birchfield, S., Wang, S., Kumar, R., Anastasiu, D., & Hwang, J. N. (2019). Cityflow: A city-scale benchmark for multi-target multi-camera vehicle tracking and re-identification. In CVPR (pp. 8797\u20138806).","DOI":"10.1109\/CVPR.2019.00900"},{"key":"2284_CR162","doi-asserted-by":"crossref","unstructured":"Tang, Z., Zhang, R., Peng, Z., Chen, J., & Lin, L. (2022). Multi-stage spatio-temporal aggregation transformer for video person re-identification. In IEEE TMM.","DOI":"10.1109\/TMM.2022.3231103"},{"key":"2284_CR163","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1007\/s11263-020-01402-2","volume":"129","author":"S Teng","year":"2021","unstructured":"Teng, S., Zhang, S., Huang, Q., & Sebe, N. (2021). Viewpoint and scale consistency reinforcement for uav vehicle re-identification. IJCV, 129, 719\u2013735.","journal-title":"IJCV"},{"key":"2284_CR164","doi-asserted-by":"crossref","unstructured":"Tian, X., Liu, J., Zhang, Z., Wang, C., Qu, Y., Xie, Y., & Ma, L. (2022). Hierarchical walking transformer for object re-identification. In ACM MM (pp. 4224\u20134232).","DOI":"10.1145\/3503161.3548401"},{"key":"2284_CR165","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. NeurIPS 30"},{"key":"2284_CR166","doi-asserted-by":"crossref","unstructured":"Walmer, M., Suri, S., Gupta, K., & Shrivastava, A. (2023). Teaching matters: Investigating the role of supervision in vision transformers. In CVPR (pp. 7486\u20137496).","DOI":"10.1109\/CVPR52729.2023.00723"},{"key":"2284_CR167","doi-asserted-by":"crossref","unstructured":"Wang, D., & Zhang, S. (2020). Unsupervised person re-identification via multi-label classification. In CVPR (pp. 10981\u201310990).","DOI":"10.1109\/CVPR42600.2020.01099"},{"key":"2284_CR168","doi-asserted-by":"crossref","unstructured":"Wang, G., Zhang, T., Cheng, J., Liu, S., Yang, Y., & Hou, Z. (2019a). Rgb-infrared cross-modality person re-identification via joint pixel and feature alignment. In ICCV (pp. 3623\u20133632).","DOI":"10.1109\/ICCV.2019.00372"},{"key":"2284_CR169","doi-asserted-by":"crossref","unstructured":"Wang, G., Yang, S., Liu, H., Wang, Z., Yang, Y., Wang, S., Yu, G., Zhou, E., & Sun, J. (2020a). High-order information matters: Learning relation and topology for occluded person re-identification. In CVPR (pp. 6449\u20136458).","DOI":"10.1109\/CVPR42600.2020.00648"},{"key":"2284_CR170","unstructured":"Wang, G., Yu, F., Li, J., Jia, Q., & Ding, S. (2023a). Exploiting the textual potential from vision-language pre-training for text-based person search. arXiv preprint arXiv:2303.04497"},{"key":"2284_CR171","doi-asserted-by":"crossref","first-page":"12144","DOI":"10.1609\/aaai.v34i07.6894","volume":"34","author":"GA Wang","year":"2020","unstructured":"Wang, G. A., Zhang, T., Yang, Y., Cheng, J., Chang, J., Liang, X., & Hou, Z. G. (2020). Cross-modality paired-images generation for rgb-infrared person re-identification. AAAI, 34, 12144\u201312151.","journal-title":"AAAI"},{"key":"2284_CR172","doi-asserted-by":"crossref","unstructured":"Wang, H., Shen, J., Liu, Y., Gao, Y., & Gavves, E. (2022a). Nformer: Robust person re-identification with neighbor transformer. In CVPR (pp. 7297\u20137307).","DOI":"10.1109\/CVPR52688.2022.00715"},{"key":"2284_CR173","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, Z., Chen, M., Zhang, Y., Wang, C., Sheng, B., Qu, Y., & Xie, Y. (2022b). Optimal transport for label-efficient visible-infrared person re-identification. In ECCV (pp. 93\u2013109). Springer.","DOI":"10.1007\/978-3-031-20053-3_6"},{"key":"2284_CR174","first-page":"2837","volume":"30","author":"L Wang","year":"2021","unstructured":"Wang, L., Ding, R., Zhai, Y., Zhang, Q., Tang, W., Zheng, N., & Hua, G. (2021). Giant panda identification. IEEE TIP, 30, 2837\u20132849.","journal-title":"Giant panda identification. IEEE TIP"},{"key":"2284_CR175","doi-asserted-by":"crossref","unstructured":"Wang, P., Jiao, B., Yang, L., Yang, Y., Zhang, S., Wei, W., & Zhang, Y. (2019b). Vehicle re-identification in aerial imagery: Dataset and approach. In ICCV (pp. 460\u2013469).","DOI":"10.1109\/ICCV.2019.00055"},{"key":"2284_CR176","doi-asserted-by":"crossref","first-page":"2540","DOI":"10.1609\/aaai.v36i3.20155","volume":"36","author":"T Wang","year":"2022","unstructured":"Wang, T., Liu, H., Song, P., Guo, T., & Shi, W. (2022). Pose-guided feature disentangling for occluded person re-identification based on transformer. AAAI, 36, 2540\u20132549.","journal-title":"AAAI"},{"key":"2284_CR177","doi-asserted-by":"crossref","unstructured":"Wang, T., Liu, H., Li, W., Ban, M., Guo, T., & Li, Y. (2023b). Feature completion transformer for occluded person re-identification. arXiv preprint arXiv:2303.01656","DOI":"10.1109\/TMM.2024.3379908"},{"key":"2284_CR178","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D. P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2021b). Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. arXiv preprint arXiv:2102.12122","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"2284_CR179","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, X., Jiang, B., & Luo, B. (2023c). Few-shot learning meets transformer: Unified query-support transformers for few-shot classification. In IEEE TCSVT","DOI":"10.1109\/TCSVT.2023.3282777"},{"key":"2284_CR180","first-page":"3321","volume":"17","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Qi, G., Li, S., Chai, Y., & Li, H. (2022). Body part-level domain alignment for domain-adaptive person re-identification with transformer framework. IEEE TIFS, 17, 3321\u20133334.","journal-title":"IEEE TIFS"},{"key":"2284_CR181","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, Z., Zheng, Y., Chuang, Y. Y., & Satoh, S. (2019c). Learning to reduce dual-level discrepancy for infrared-visible person re-identification. In CVPR (pp. 618\u2013626).","DOI":"10.1109\/CVPR.2019.00071"},{"key":"2284_CR182","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, Z., Zheng, Y., Wu, Y., Zeng, W., & Satoh, S. (2019d). Beyond intra-modality: A survey of heterogeneous person re-identification. arXiv preprint arXiv:1905.10048","DOI":"10.24963\/ijcai.2020\/692"},{"key":"2284_CR183","doi-asserted-by":"crossref","unstructured":"Wang, Z., Fang, Z., Wang, J., & Yang, Y. (2020c). Vitaa: Visual-textual attributes alignment in person search by natural language. In ECCV (pp. 402\u2013420). Springer.","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"2284_CR184","doi-asserted-by":"crossref","unstructured":"Wei, L., Zhang, S., Gao, W., & Tian, Q. (2018). Person transfer gan to bridge domain gap for person re-identification. In CVPR (pp. 79\u201388).","DOI":"10.1109\/CVPR.2018.00016"},{"issue":"3","key":"2284_CR185","first-page":"2935","volume":"24","author":"R Wei","year":"2022","unstructured":"Wei, R., Gu, J., He, S., & Jiang, W. (2022). Transformer-based domain-specific representation for unsupervised domain adaptive vehicle re-identification. IEEE TITS, 24(3), 2935\u20132946.","journal-title":"IEEE TITS"},{"key":"2284_CR186","doi-asserted-by":"crossref","unstructured":"Weideman, H., Stewart, C., Parham, J., Holmberg, J., Flynn, K., Calambokidis, J., Paul, D. B., Bedetti, A., Henley M., & Pope F., et\u00a0al. (2020). Extracting identifying contours for african elephants and humpback whales using a learned appearance model. In WACV (pp. 1276\u20131285).","DOI":"10.1109\/WACV45572.2020.9093266"},{"key":"2284_CR187","doi-asserted-by":"crossref","unstructured":"Weideman, H. J., Jablons, Z. M., Holmberg, J., Flynn, K., Calambokidis, J., Tyson, R. B., Allen, J. B., Wells, R. S., Hupman, K., & Urian K., et\u00a0al. (2017). Integral curvature representation and matching algorithms for identification of dolphins and whales. In ICCV workshop (pp. 2831\u20132839).","DOI":"10.1109\/ICCVW.2017.334"},{"key":"2284_CR188","doi-asserted-by":"crossref","unstructured":"Wu, A., Zheng, W. S., Yu, H. X., Gong, S., & Lai, J. (2017). Rgb-infrared cross-modality person re-identification. In ICCV (pp. 5380\u20135389).","DOI":"10.1109\/ICCV.2017.575"},{"key":"2284_CR189","doi-asserted-by":"crossref","unstructured":"Wu, J., He, L., Liu, W., Yang, Y., Lei, Z., Mei, T., & Li, S. Z. (2022a). Cavit: Contextual alignment vision transformer for video object re-identification. In ECCV (pp. 549\u2013566). Springer.","DOI":"10.1007\/978-3-031-19781-9_32"},{"key":"2284_CR190","first-page":"4803","volume":"31","author":"L Wu","year":"2022","unstructured":"Wu, L., Liu, D., Zhang, W., Chen, D., Ge, Z., Boussaid, F., Bennamoun, M., & Shen, J. (2022). Pseudo-pair based self-similarity learning for unsupervised person re-identification. IEEE TIP, 31, 4803\u20134816.","journal-title":"IEEE TIP"},{"key":"2284_CR191","doi-asserted-by":"crossref","first-page":"6083","DOI":"10.1609\/aaai.v38i6.28424","volume":"38","author":"P Wu","year":"2024","unstructured":"Wu, P., Wang, L., Zhou, S., Hua, G., & Sun, C. (2024). Temporal correlation vision transformer for video person re-identification. AAAI, 38, 6083\u20136091.","journal-title":"AAAI"},{"key":"2284_CR192","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yan, Z., Han, X., Li, G., Zou, C., & Cui, S. (2021). Lapscore: language-guided person search via color reasoning. In ICCV (pp. 1624\u20131633).","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"2284_CR193","doi-asserted-by":"crossref","unstructured":"Wu, Z., & Ye, M. (2023). Unsupervised visible-infrared person re-identification via progressive graph matching and alternate learning. In CVPR (pp. 9548\u20139558).","DOI":"10.1109\/CVPR52729.2023.00921"},{"key":"2284_CR194","doi-asserted-by":"crossref","unstructured":"Xiao, H., Lin, W., Sheng, B., Lu, K., Yan, J., Wang, J., Ding, E., & Zhang, Y., Xiong, H. (2018). Group re-identification: Leveraging and integrating multi-grain information. In ACM MM (pp. 192\u2013200).","DOI":"10.1145\/3240508.3240539"},{"key":"2284_CR195","doi-asserted-by":"crossref","unstructured":"Xiao, T., Li, S., Wang, B., Lin, L., & Wang, X. (2017). Joint detection and identification feature learning for person search. In CVPR (pp. 3415\u20133424).","DOI":"10.1109\/CVPR.2017.360"},{"key":"2284_CR196","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., Dai, Q., & Hu, H. (2022). Simmim: A simple framework for masked image modeling. In CVPR (pp. 9653\u20139663).","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"2284_CR197","first-page":"4651","volume":"31","author":"B Xu","year":"2022","unstructured":"Xu, B., He, L., Liang, J., & Sun, Z. (2022). Learning feature recovery transformer for occluded person re-identification. IEEE TIP, 31, 4651\u20134662.","journal-title":"IEEE TIP"},{"key":"2284_CR198","doi-asserted-by":"crossref","unstructured":"Xu, P., Zhu, X. (2023). Deepchange: A long-term person re-identification benchmark with clothes change. In ICCV (pp. 11196\u201311205).","DOI":"10.1109\/ICCV51070.2023.01028"},{"key":"2284_CR199","doi-asserted-by":"crossref","unstructured":"Xu, P., Zhu, X., & Clifton, D. A. (2023). Multimodal learning with transformers: A survey. In IEEE TPAMI.","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"2284_CR200","doi-asserted-by":"crossref","unstructured":"Xu, W., Liu, H., Shi, W., Miao, Z., Lu, Z., & Chen, F. (2021). Adversarial feature disentanglement for long-term person re-identification. In IJCAI (pp. 1201\u20131207).","DOI":"10.24963\/ijcai.2021\/166"},{"key":"2284_CR201","doi-asserted-by":"crossref","unstructured":"Xuan, S., Zhang, S. (2021). Intra-inter camera similarity for unsupervised person re-identification. In CVPR (pp. 11926\u201311935).","DOI":"10.1109\/CVPR46437.2021.01175"},{"key":"2284_CR202","doi-asserted-by":"crossref","unstructured":"Yan, K., Tian, Y., Wang, Y., Zeng, W., & Huang, T. (2017). Exploiting multi-grain ranking constraints for precisely searching visually-similar vehicles. In ICCV (pp. 562\u2013570).","DOI":"10.1109\/ICCV.2017.68"},{"key":"2284_CR203","doi-asserted-by":"crossref","unstructured":"Yan, S., Dong, N., Zhang, L., & Tang, J. (2022). Clip-driven fine-grained text-image person re-identification. arXiv preprint arXiv:2210.10276","DOI":"10.1109\/TIP.2023.3327924"},{"key":"2284_CR204","doi-asserted-by":"crossref","unstructured":"Yan, Y., Ni, B., Song, Z., Ma, C., Yan, Y., & Yang, X. (2016). Person re-identification via recurrent feature aggregation. In ECCV (pp. 701\u2013716). Springer","DOI":"10.1007\/978-3-319-46466-4_42"},{"issue":"6","key":"2284_CR205","doi-asserted-by":"crossref","first-page":"7001","DOI":"10.1109\/TPAMI.2020.3032542","volume":"45","author":"Y Yan","year":"2020","unstructured":"Yan, Y., Qin, J., Ni, B., Chen, J., Liu, L., Zhu, F., Zheng, W. S., Yang, X., & Shao, L. (2020). Learning multi-attention context graph for group-based re-identification. IEEE TPAMI, 45(6), 7001\u20137018.","journal-title":"IEEE TPAMI"},{"key":"2284_CR206","doi-asserted-by":"crossref","unstructured":"Yang, B., Ye, M., Chen, J., & Wu, Z. (2022). Augmented dual-contrastive aggregation learning for unsupervised visible-infrared person re-identification. In ACM MM (pp. 2843\u20132851).","DOI":"10.1145\/3503161.3548198"},{"key":"2284_CR207","doi-asserted-by":"crossref","unstructured":"Yang, B., Chen, J., & Ye, M. (2023a). Top-k visual tokens transformer: Selecting tokens for visible-infrared person re-identification. In ICASSP (pp. 1\u20135). IEEE.","DOI":"10.1109\/ICASSP49357.2023.10097170"},{"key":"2284_CR208","doi-asserted-by":"crossref","unstructured":"Yang, B., Chen, J., Ye, M. (2023b). Towards grand unified representation learning for unsupervised visible-infrared person re-identification. In ICCV (pp. 11069\u201311079).","DOI":"10.1109\/ICCV51070.2023.01016"},{"issue":"6","key":"2284_CR209","doi-asserted-by":"crossref","first-page":"2029","DOI":"10.1109\/TPAMI.2019.2960509","volume":"43","author":"Q Yang","year":"2019","unstructured":"Yang, Q., Wu, A., & Zheng, W. S. (2019). Person re-identification by contour sketch under moderate clothing change. IEEE TPAMI, 43(6), 2029\u20132046.","journal-title":"IEEE TPAMI"},{"key":"2284_CR210","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhou, Y., Zheng, Z., Wang, Y., Zhu, L., & Wu, Y. (2023c). Towards unified text-based person retrieval: A large-scale multi-attribute and language search benchmark. In ACM MM (pp. 4492\u20134501).","DOI":"10.1145\/3581783.3611709"},{"key":"2284_CR211","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wu, D., Wu, C., Lin, Z., Gu, J., & Wang, W. (2024). A pedestrian is worth one prompt: Towards language guidance person re-identification. In CVPR (pp. 17343\u201317353)","DOI":"10.1109\/CVPR52733.2024.01642"},{"key":"2284_CR212","doi-asserted-by":"crossref","unstructured":"Yao, Y., Zheng, L., Yang, X., Naphade, M., & Gedeon, T. (2020). Simulating content consistent vehicle datasets with attribute descent. In ECCV (pp. 775\u2013791). Springer.","DOI":"10.1007\/978-3-030-58539-6_46"},{"key":"2284_CR213","doi-asserted-by":"crossref","unstructured":"Ye, M., Liang, C., Wang, Z., Leng, Q., Chen, J., & Liu, J. (2015). Specific person retrieval via incomplete text description. In ACM ICMRl (pp. 547\u2013550).","DOI":"10.1145\/2671188.2749347"},{"key":"2284_CR214","doi-asserted-by":"crossref","unstructured":"Ye, M., Lan, X., Li, J., Yuen, P. (2018). Hierarchical discriminative learning for visible thermal person re-identification. In AAAI (vol.\u00a032).","DOI":"10.1609\/aaai.v32i1.12293"},{"issue":"1","key":"2284_CR215","first-page":"615","volume":"16","author":"M Ye","year":"2019","unstructured":"Ye, M., Cheng, Y., Lan, X., & Zhu, H. (2019). Improving night-time pedestrian retrieval with distribution alignment and contextual distance. IEEE TII, 16(1), 615\u2013624.","journal-title":"IEEE TII"},{"key":"2284_CR216","first-page":"407","volume":"15","author":"M Ye","year":"2019","unstructured":"Ye, M., Lan, X., Wang, Z., & Yuen, P. C. (2019). Bi-directional center-constrained top-ranking for visible thermal person re-identification. IEEE TIFS, 15, 407\u2013419.","journal-title":"IEEE TIFS"},{"key":"2284_CR217","first-page":"728","volume":"16","author":"M Ye","year":"2020","unstructured":"Ye, M., Shen, J., & Shao, L. (2020). Visible-infrared person re-identification via homogeneous augmented tri-modal learning. IEEE TIFS, 16, 728\u2013739.","journal-title":"IEEE TIFS"},{"key":"2284_CR218","unstructured":"Ye, M., Shen, J., Zhang, X., Yuen, P. C., & Chang, S. F. (2020b). Augmentation invariant and instance spreading feature for softmax embedding. In IEEE TPAMI."},{"key":"2284_CR219","first-page":"379","volume":"31","author":"M Ye","year":"2021","unstructured":"Ye, M., Li, H., Du, B., Shen, J., Shao, L., & Hoi, S. C. (2021). Collaborative refining for person re-identification with label noise. IEEE TIP, 31, 379\u2013391.","journal-title":"IEEE TIP"},{"key":"2284_CR220","doi-asserted-by":"crossref","unstructured":"Ye, M., Ruan, W., Du, B., & Shou, M. Z. (2021b). Channel augmented joint learning for visible-infrared recognition. In ICCV (pp. 13567\u201313576).","DOI":"10.1109\/ICCV48922.2021.01331"},{"key":"2284_CR221","unstructured":"Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., & Hoi, S. C. H. (2021c). Deep learning for person re-identification: A survey and outlook. In IEEE TPAMI (pp. 1\u20131)."},{"key":"2284_CR222","first-page":"1","volume":"01","author":"M Ye","year":"2023","unstructured":"Ye, M., Wu, Z., Chen, C., & Du, B. (2023). Channel augmentation for visible-infrared re-identification. IEEE TPAMI, 01, 1\u201316.","journal-title":"IEEE TPAMI"},{"key":"2284_CR223","unstructured":"Ye, Y., Zhou, H., Yu, J., Hu, Q., & Yang, W. (2022). Dynamic feature pruning and consolidation for occluded person re-identification. arXiv preprint arXiv:2211.14742"},{"key":"2284_CR224","doi-asserted-by":"crossref","unstructured":"Yu, H. X., Zheng, W. S., Wu, A., Guo, X., Gong, S., & Lai, J. H. (2019). Unsupervised person re-identification by soft multilabel learning. In CVPR (pp. 2148\u20132157).","DOI":"10.1109\/CVPR.2019.00225"},{"key":"2284_CR225","doi-asserted-by":"crossref","unstructured":"Yu, R., Du, D., LaLonde, R., Davila, D., Funk, C., Hoogs, A., & Clipp, B. (2022). Cascade transformers for end-to-end person search. In CVPR (pp. 7267\u20137276).","DOI":"10.1109\/CVPR52688.2022.00712"},{"key":"2284_CR226","doi-asserted-by":"crossref","unstructured":"Zapletal, D., & Herout, A. (2016). Vehicle re-identification for automatic video traffic surveillance. In CVPR workshop (pp. 25\u201331).","DOI":"10.1109\/CVPRW.2016.195"},{"key":"2284_CR227","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., & Beyer, L. (2022a). Scaling vision transformers. In CVPR (pp. 12104\u201312113).","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"2284_CR228","doi-asserted-by":"crossref","unstructured":"Zhai, Y., Zeng, Y., Cao, D., & Lu, S. (2022b). Trireid: Towards multi-modal person re-identification via descriptive fusion model. In ICMR (pp. 63\u201371).","DOI":"10.1145\/3512527.3531397"},{"key":"2284_CR229","doi-asserted-by":"crossref","unstructured":"Zhang, B., Liang, Y., & Du, M. (2022a). Interlaced perception for person re-identification based on swin transformer. In IEEE ICIVC (pp. 24\u201330).","DOI":"10.1109\/ICIVC55077.2022.9886403"},{"key":"2284_CR230","doi-asserted-by":"crossref","unstructured":"Zhang, G., Zhang, P., Qi, J., & Lu, H. (2021a). Hat: Hierarchical aggregation transformers for person re-identification. In ACM MM (pp. 516\u2013525).","DOI":"10.1145\/3474085.3475202"},{"key":"2284_CR231","doi-asserted-by":"crossref","unstructured":"Zhang, G., Zhang, Y., Zhang, T., Li, B., & Pu, S. (2023a). Pha: Patch-wise high-frequency augmentation for transformer-based person re-identification. In CVPR (pp. 14133\u201314142).","DOI":"10.1109\/CVPR52729.2023.01358"},{"key":"2284_CR232","doi-asserted-by":"crossref","first-page":"3318","DOI":"10.1609\/aaai.v36i3.20241","volume":"36","author":"Q Zhang","year":"2022","unstructured":"Zhang, Q., Lai, J. H., Feng, Z., & Xie, X. (2022). Uncertainty modeling with second-order transformer for group re-identification. AAAI, 36, 3318\u20133325.","journal-title":"AAAI"},{"key":"2284_CR233","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Wang, L., Patel, V. M., Xie, X., & Lai, J. (2024). View-decoupled transformer for person re-identification under aerial-ground camera network. In CVPR (pp. 22000\u201322009).","DOI":"10.1109\/CVPR52733.2024.02077"},{"key":"2284_CR234","first-page":"281","volume":"23","author":"S Zhang","year":"2020","unstructured":"Zhang, S., Zhang, Q., Yang, Y., Wei, X., Wang, P., Jiao, B., & Zhang, Y. (2020). Person re-identification in aerial imagery. IEEE TMM, 23, 281\u2013291.","journal-title":"IEEE TMM"},{"key":"2284_CR235","first-page":"8861","volume":"30","author":"S Zhang","year":"2021","unstructured":"Zhang, S., Yang, Y., Wang, P., Liang, G., Zhang, X., & Zhang, Y. (2021). Attend to the difference: Cross-modality person re-identification via contrastive correlation. IEEE TIP, 30, 8861\u20138872.","journal-title":"IEEE TIP"},{"key":"2284_CR236","unstructured":"Zhang, T., Wei, L., Xie, L., Zhuang, Z., Zhang, Y., Li, B., & Tian, Q. (2021c). Spatiotemporal transformer for video-based person re-identification. arXiv preprint arXiv:2103.16469"},{"key":"2284_CR237","doi-asserted-by":"crossref","unstructured":"Zhang, T., Xie, L., Wei, L., Zhuang, Z., Zhang, Y., Li, B., & Tian, Q. (2021d). Unrealperson: An adaptive pipeline towards costless person re-identification. In CVPR (pp. 11506\u201311515).","DOI":"10.1109\/CVPR46437.2021.01134"},{"key":"2284_CR238","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zhao, Q., Da, C., Zhou, L., Li, L., & Jiancuo, S. (2021e). Yakreid-103: A benchmark for yak re-identification. In IEEE IJCB (pp. 1\u20138). IEEE.","DOI":"10.1109\/IJCB52358.2021.9484341"},{"key":"2284_CR239","doi-asserted-by":"crossref","unstructured":"Zhang, X., Ge, Y., Qiao, Y., & Li, H. (2021f). Refining pseudo labels with clustering consensus over generations for unsupervised object re-identification. In CVPR (pp. 3436\u20133445).","DOI":"10.1109\/CVPR46437.2021.00344"},{"key":"2284_CR240","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, D., Wang, Z., Wang, J., Ding, E., Shi, J. Q., Zhang, Z., & Wang, J. (2022c). Implicit sample extension for unsupervised person re-identification. In CVPR pp. 7369\u20137378.","DOI":"10.1109\/CVPR52688.2022.00722"},{"key":"2284_CR241","doi-asserted-by":"crossref","unstructured":"Zhang, Y., & Lu, H. (2018). Deep cross-modal projection learning for image-text matching. In ECCV (pp. 686\u2013701).","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"2284_CR242","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, Y., Li, H., & Li, S. (2022d). Cross-compatible embedding and semantic consistent feature construction for sketch re-identification. In ACM MM (pp. 3347\u20133355).","DOI":"10.1145\/3503161.3548224"},{"key":"2284_CR243","unstructured":"Zhang, Y., Gong, K., Zhang, K., Li, H., Qiao, Y., Ouyang, W., & Yue, X. (2023b). Meta-transformer: A unified framework for multimodal learning. arXiv preprint arXiv:2307.10802"},{"key":"2284_CR244","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Lan, C., Zeng, W., Jin, X., & Chen, Z. (2020b). Relation-aware global attention for person re-identification. In CVPR (pp. 3186\u20133195).","DOI":"10.1109\/CVPR42600.2020.00325"},{"key":"2284_CR245","doi-asserted-by":"crossref","unstructured":"Zhao, J., Wang, H., Zhou, Y., Yao, R., Chen, S., & El\u00a0Saddik, A. (2022). Spatial-channel enhanced transformer for visible-infrared person re-identification. In IEEE TMM.","DOI":"10.1109\/TMM.2022.3163847"},{"key":"2284_CR246","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhong, Z., Yang, F., Luo, Z., Lin, Y., Li, S., & Sebe, N. (2021). Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification. In CVPR (pp. 6277\u20136286).","DOI":"10.1109\/CVPR46437.2021.00621"},{"key":"2284_CR247","doi-asserted-by":"crossref","unstructured":"Zheng, K., Liu, W., He, L., Mei, T., Luo, J., & Zha, Z. J. (2021). Group-aware label transfer for domain adaptive person re-identification. In CVPR (pp. 5310\u20135319).","DOI":"10.1109\/CVPR46437.2021.00527"},{"key":"2284_CR248","doi-asserted-by":"crossref","unstructured":"Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., & Tian, Q. (2015). Scalable person re-identification: A benchmark. In ICCV (pp. 1116\u20131124).","DOI":"10.1109\/ICCV.2015.133"},{"key":"2284_CR249","doi-asserted-by":"crossref","unstructured":"Zheng, L., Bie, Z., Sun, Y., Wang, J., Su, C., Wang, S., & Tian, Q. (2016a). Mars: A video benchmark for large-scale person re-identification. In ECCV (pp. 868\u2013884). Springer.","DOI":"10.1007\/978-3-319-46466-4_52"},{"key":"2284_CR250","unstructured":"Zheng, L., Yang, Y., & Hauptmann, A. G. (2016b). Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984"},{"key":"2284_CR251","doi-asserted-by":"crossref","unstructured":"Zheng, L., Zhang, H., Sun, S., Chandraker, M., Yang, Y., & Tian, Q. (2017a). Person re-identification in the wild. In CVPR (pp. 1367\u20131376).","DOI":"10.1109\/CVPR.2017.357"},{"key":"2284_CR252","doi-asserted-by":"crossref","unstructured":"Zheng, W., Gong, S., & Xiang, T. (2009). Associating groups of people. In BMVC (pp. 1\u201311).","DOI":"10.5244\/C.23.23"},{"issue":"1","key":"2284_CR253","first-page":"1","volume":"14","author":"Z Zheng","year":"2017","unstructured":"Zheng, Z., Zheng, L., & Yang, Y. (2017). A discriminatively learned cnn embedding for person reidentification. ACM TOMM, 14(1), 1\u201320.","journal-title":"ACM TOMM"},{"key":"2284_CR254","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zheng, L., & Yang, Y. (2017c). Unlabeled samples generated by gan improve the person re-identification baseline in vitro. In ICCV (pp. 3754\u20133762).","DOI":"10.1109\/ICCV.2017.405"},{"key":"2284_CR255","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Cao, D., & Li, S. (2017). Re-ranking person re-identification with k-reciprocal encoding. In CVPR (pp. 1318\u20131327).","DOI":"10.1109\/CVPR.2017.389"},{"key":"2284_CR256","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, Y., Cavallaro, A., & Xiang, T. (2019). Omni-scale feature learning for person re-identification. In ICCV (pp. 3702\u20133712).","DOI":"10.1109\/ICCV.2019.00380"},{"issue":"9","key":"2284_CR257","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022). Learning to prompt for vision-language models. IJCV, 130(9), 2337\u20132348.","journal-title":"IJCV"},{"key":"2284_CR258","unstructured":"Zhou, M., Liu, H., Lv, Z., Hong, W., & Chen, X. (2022b). Motion-aware transformer for occluded person re-identification. arXiv preprint arXiv:2202.04243"},{"key":"2284_CR259","doi-asserted-by":"crossref","unstructured":"Zhu, A., Wang, Z., Li, Y., Wan, X., Jin, J., Wang, T., Hu, F., & Hua, G. (2021a). Dssl: Deep surroundings-person separation learning for text-based person retrieval. In ACM MM (pp. 209\u2013217).","DOI":"10.1145\/3474085.3475369"},{"key":"2284_CR260","doi-asserted-by":"crossref","unstructured":"Zhu, H., Ke, W., Li, D., Liu, J., Tian, L., & Shan, Y. (2022a). Dual cross-attention learning for fine-grained visual categorization and object re-identification. In CVPR (pp. 4692\u20134702).","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"2284_CR261","unstructured":"Zhu, K., Guo, H., Zhang, S., Wang, Y., Huang, G., Qiao, H., Liu, J., Wang, J., & Tang, M. (2021b). Aaformer: Auto-aligned transformer for person re-identification. arXiv preprint arXiv:2104.00921"},{"key":"2284_CR262","doi-asserted-by":"crossref","unstructured":"Zhu, K., Guo, H., Yan, T., Zhu, Y., Wang, J., & Tang, M. (2022). Pass: Part-aware self-supervised pre-training for person re-identification. ECCV (pp. 198\u2013214). Cham: Springer.","DOI":"10.1007\/978-3-031-19781-9_12"},{"key":"2284_CR263","doi-asserted-by":"crossref","unstructured":"Zhuo, J., Chen, Z., Lai, J., & Wang, G. (2018). Occluded person re-identification. In ICME (pp. 1\u20136). IEEE.","DOI":"10.1109\/ICME.2018.8486568"},{"issue":"5","key":"2284_CR264","doi-asserted-by":"crossref","first-page":"801","DOI":"10.3390\/ani13050801","volume":"13","author":"M Zuerl","year":"2023","unstructured":"Zuerl, M., Dirauf, R., Koeferl, F., Steinlein, N., Sueskind, J., Zanca, D., Brehm, I., Lv, Fersen, & Eskofier, B. (2023). Polarbearvidid: A video-based re-identification benchmark dataset for polar bears. Animals, 13(5), 801.","journal-title":"Animals"},{"key":"2284_CR265","unstructured":"Zuo, J., Yu, C., Sang, N., Gao, & C. (2023). Plip: Language-image pre-training for person representation learning. arXiv preprint arXiv:2305.08386"},{"key":"2284_CR266","doi-asserted-by":"crossref","unstructured":"Zuo, J., Zhou, H., Nie, Y., Zhang, F., Guo, T., Sang, N., Wang, Y., & Gao, C. (2024). Ufinebench: Towards text-based person retrieval with ultra-fine granularity. In CVPR (pp. 22010\u201322019).","DOI":"10.1109\/CVPR52733.2024.02078"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02284-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02284-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02284-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T06:02:54Z","timestamp":1744869774000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02284-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"references-count":266,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["2284"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02284-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"22 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}