{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T12:08:56Z","timestamp":1790078936242,"version":"4.0.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"The National Undergraduate Training Program for Innovation and Entrepreneurship","award":["No.202510058119"],"award-info":[{"award-number":["No.202510058119"]}]},{"name":"Open Project of Tianjin Key Laboratory of Optoelectronic Detection Technology and System","award":["No. 2025LODTS111"],"award-info":[{"award-number":["No. 2025LODTS111"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s10044-026-01761-5","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T02:01:33Z","timestamp":1787623293000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CATSANet: cross-modal semantic token selection and optimal transport based part alignment for text-to-image person ReID"],"prefix":"10.1007","volume":"29","author":[{"given":"Dongbin","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"key":"1761_CR1","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: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1970\u20131979","DOI":"10.1109\/CVPR.2017.551"},{"key":"1761_CR2","doi-asserted-by":"crossref","unstructured":"Jiang D, Ye M (2023) Cross-modal implicit relation reasoning and aligning for text-to-image person re-identification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2787\u20132797","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"1761_CR3","doi-asserted-by":"crossref","unstructured":"Qin Y, Chen C, Fu Z, Peng D, Peng X, Hu P (2025) Human-centered interactive learning via mllms for text-to-image person re-identification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 14390\u201314399","DOI":"10.1109\/CVPR52734.2025.01342"},{"key":"1761_CR4","doi-asserted-by":"crossref","unstructured":"Bai Y, Ji Y, Cao M, Wang J, Ye M (2025) Chat-based person retrieval via dialogue-refined cross-modal alignment. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 3952\u20133962","DOI":"10.1109\/CVPR52734.2025.00374"},{"key":"1761_CR5","doi-asserted-by":"crossref","unstructured":"Li Z (2025) Exploring the potential of large vision-language models for unsupervised text-based person retrieval. In: Proceedings of the AAAI conference on artificial intelligence, vol 39, pp 5119\u20135127","DOI":"10.1609\/aaai.v39i5.32543"},{"key":"1761_CR6","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J (2021) Learning transferable visual models from natural language supervision. In: International conference on machine learning, pp 8748\u20138763 (PMLR)"},{"key":"1761_CR7","unstructured":"Wang X, Chen R, Shirian A (2022) Img-text: implicit visual-textual alignment for text-to-image person re-identification. In: European conference on computer vision. Springer, pp 1\u201317"},{"key":"1761_CR8","first-page":"561","volume":"33","author":"S Yan","year":"2023","unstructured":"Yan S, Dong N, Zhang L, Tang J (2023) Clip-driven fine-grained text-image person re-identification. IEEE Trans Image Process 33:561\u2013574","journal-title":"IEEE Trans Image Process"},{"key":"1761_CR9","doi-asserted-by":"crossref","unstructured":"Kim G, Eom C (2026) Dico: Disentangled concept representation for text-to-image person re-identification. arXiv preprint arXiv:2601.10053","DOI":"10.1016\/j.neucom.2026.132885"},{"key":"1761_CR10","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":"1761_CR11","unstructured":"Wang Z, Wang A, Li J, et\u00a0al (2022) Caapc: cross-modal alignment with attribute-prompted contrastive learning for text-to-image person re-identification. In: Proceedings of the 30th ACM international conference on multimedia, pp 1\u201310"},{"key":"1761_CR12","unstructured":"Chen S (2022) Learning both unique and latent features for text-based person retrieval. In: Proceedings of the 30th ACM international conference on multimedia, pp 1\u20139"},{"key":"1761_CR13","doi-asserted-by":"crossref","unstructured":"Xu Y, Wu J, Gao D, Chen Z, Yang Y, Cao M, Ye M, Lei Z (2025) Sa-person: text-based person retrieval with scene-aware re-ranking. arXiv preprint arXiv:2505.24466","DOI":"10.1109\/TIFS.2026.3707789"},{"key":"1761_CR14","unstructured":"Rao Y, Zhao W, Liu B, Lu J, Zhou J, Hsieh C-J (2021) Dynamicvit: Efficient vision transformers with dynamic token sparsification. Advances in Neural Information Processing Systems, vol 34, pp 13937\u201313949"},{"key":"1761_CR15","unstructured":"Gao G (2023) Optimal transport for cross-modal alignment. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition"},{"key":"1761_CR16","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.neucom.2022.04.081","volume":"494","author":"Y Chen","year":"2021","unstructured":"Chen Y, Zhang G, Lu Y, Wang Z, Zheng Y, Wang R (2021) Tipcb: a simple but effective part-based convolutional baseline for text-based person search. Neurocomputing 494:171\u2013181","journal-title":"Neurocomputing"},{"key":"1761_CR17","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I (2021) Learning transferable visual models from natural language supervision. In: International conference on machine learning. https:\/\/api.semanticscholar.org\/CorpusID:231591445"},{"key":"1761_CR18","doi-asserted-by":"crossref","unstructured":"Chen Y-C, Li L, Yu L, Kholy AE, Ahmed F, Gan Z, Cheng Y, Liu J (2019) Uniter: universal image-text representation learning. In: European conference on computer vision, https:\/\/api.semanticscholar.org\/CorpusID:216080982","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"1761_CR19","unstructured":"Kim W, Son B, Kim I (2021) Vilt: vision-and-language transformer without convolution or region supervision. In: International conference on machine learning, https:\/\/api.semanticscholar.org\/CorpusID:231839613"},{"key":"1761_CR20","doi-asserted-by":"publisher","unstructured":"Jiang D, Ye M (2023) Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval. In: 2023 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 2787\u20132797. https:\/\/doi.org\/10.1109\/CVPR52729.2023.00273","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"1761_CR21","doi-asserted-by":"publisher","first-page":"6032","DOI":"10.1109\/TIP.2023.3327924","volume":"32","author":"S Yan","year":"2022","unstructured":"Yan S, Dong N, Zhang L, Tang J (2022) Clip-driven fine-grained text-image person re-identification. IEEE Trans Image Process 32:6032\u20136046","journal-title":"IEEE Trans Image Process"},{"key":"1761_CR22","doi-asserted-by":"publisher","unstructured":"Zhang D, Wu X-J, Yu J (2021) Discrete bidirectional matrix factorization hashing for zero-shot cross-media retrieval. In: Pattern recognition and computer vision. Springer, Cham, pp 524\u2013536. https:\/\/doi.org\/10.1007\/978-3-030-88007-1_43","DOI":"10.1007\/978-3-030-88007-1_43"},{"issue":"1","key":"1761_CR23","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s10044-020-00893-6","volume":"24","author":"D Zhang","year":"2021","unstructured":"Zhang D, Wu X-J, Yu J (2021) Learning latent hash codes with discriminative structure preserving for cross-modal retrieval. Pattern Anal Appl 24(1):283\u2013297. https:\/\/doi.org\/10.1007\/s10044-020-00893-6","journal-title":"Pattern Anal Appl"},{"key":"1761_CR24","doi-asserted-by":"publisher","unstructured":"Zhang D, Wu X-J, Liu Z, Yu J, Kittler J (2021) Fast discrete cross-modal hashing based on label relaxation and matrix factorization. In: 2020 25th International conference on pattern recognition (ICPR), pp 4845\u20134850. https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412497","DOI":"10.1109\/ICPR48806.2021.9412497"},{"key":"1761_CR25","doi-asserted-by":"publisher","unstructured":"Zhang D, Wu X-J (2022) Robust and discrete matrix factorization hashing for cross-modal retrieval. Pattern Recognit 122:108343. https:\/\/doi.org\/10.1016\/j.patcog.2021.108343","DOI":"10.1016\/j.patcog.2021.108343"},{"key":"1761_CR26","doi-asserted-by":"crossref","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the association for computational linguistics. https:\/\/api.semanticscholar.org\/CorpusID:52967399","DOI":"10.18653\/v1\/N19-1423"},{"key":"1761_CR27","unstructured":"Vaswani A, Shazeer NM, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Neural information processing systems. https:\/\/api.semanticscholar.org\/CorpusID:13756489"},{"key":"1761_CR28","doi-asserted-by":"crossref","unstructured":"Dou Z-Y, Xu Y, Gan Z, Wang J, Wang S, Wang L, Zhu C, Peng N, Liu Z, Zeng M (2021) An empirical study of training end-to-end vision-and-language transformers. In: 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 18145\u201318155","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"1761_CR29","unstructured":"Jia C, Yang Y, Xia Y, Chen Y-T, Parekh Z, Pham H, Le QV, Sung Y-H, Li Z, Duerig T (2021) Scaling up visual and vision-language representation learning with noisy text supervision. arXiv:2102.05918"},{"key":"1761_CR30","doi-asserted-by":"publisher","unstructured":"Wu W, Song S, Qiu X, Huang X, Ma F, Xiao J (2025) Image fusion for cross-domain sequential recommendation. In: Companion proceedings of the ACM on web conference 2025. WWW \u201925, pp 2196\u20132202. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3701716.3717566","DOI":"10.1145\/3701716.3717566"},{"key":"1761_CR31","doi-asserted-by":"crossref","unstructured":"Wu W, Chen Z, Qiu X, Song S, Huang X, Ma F, Xiao J (2025) Llm-enhanced multimodal fusion for cross-domain sequential recommendation. arXiv preprint arXiv:2506.17966","DOI":"10.1016\/j.eswa.2026.132228"},{"issue":"1","key":"1761_CR32","doi-asserted-by":"publisher","first-page":"1130","DOI":"10.1109\/TCE.2025.3620527","volume":"72","author":"W Wu","year":"2026","unstructured":"Wu W, Chen X, Chen Z, Jiang J-E, Tsang K-F, Huang X, Ma F, Xiao J (2026) Tag-enriched multi-attention with large language models for cross-domain sequential recommendation. IEEE Trans Consum Electron 72(1):1130\u20131137. https:\/\/doi.org\/10.1109\/TCE.2025.3620527","journal-title":"IEEE Trans Consum Electron"},{"key":"1761_CR33","doi-asserted-by":"publisher","unstructured":"Wu W, Chen Z, Ma X, Zhang W, Qiu X, Song S, Huang X, Ma F, Xiao J (2026) Contrastive prompt clustering for weakly supervised semantic segmentation. Expert Systems with Applications 316:131880. https:\/\/doi.org\/10.1016\/j.eswa.2026.131880","DOI":"10.1016\/j.eswa.2026.131880"},{"key":"1761_CR34","doi-asserted-by":"publisher","unstructured":"Zhang Y, Zhen J, Sun S, Liu T, Huo L, Wang T (2026) Scafnet: A semantic compensated adaptive fusion network for remote sensing images change detection. IEEE Geosci Remote Sens Lett 23:1\u20135. https:\/\/doi.org\/10.1109\/LGRS.2025.3650414","DOI":"10.1109\/LGRS.2025.3650414"},{"key":"1761_CR35","doi-asserted-by":"publisher","unstructured":"Zhang Y, Wang T, Xue L, Lian W, Tao R (2026) Orsi salient object detection via progressive interaction and saliency-guided enhancement. IEEE Geosci Remote Sens Lett 23:1\u20135. https:\/\/doi.org\/10.1109\/LGRS.2025.3645633","DOI":"10.1109\/LGRS.2025.3645633"},{"key":"1761_CR36","doi-asserted-by":"crossref","unstructured":"Zhang Y, Lu H (2018) Deep cross-modal projection learning for image-text matching. In: Proceedings of the European conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"1761_CR37","doi-asserted-by":"crossref","unstructured":"Sarafianos N, Xu X, Kakadiaris IA (2019) Adversarial representation learning for text-to-image matching. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00591"},{"key":"1761_CR38","unstructured":"Wang Z, Fang Z, Wang J, Yang Y (2020) Vitaa: visual-textual attributes alignment in person search by natural language. In: Computer vision\u2014ECCV 2020, pp 392\u2013408. 10.1007\/978-3-030-58545-8_23 . Springer. https:\/\/www.ecva.net\/papers\/eccv_2020\/papers_ECCV\/papers\/123570392.pdf"},{"key":"1761_CR39","doi-asserted-by":"crossref","unstructured":"Zhu A, Wang Z, Li Y, Wan X, Jin J, Wang T, Hu F, Hua G (2021) Dssl: deep surroundings-person separation learning for text-based person retrieval. In: Proceedings of the 29th ACM international conference on multimedia. MM \u201921, pp 209\u2013217. Association for Computing Machinery, New York, NY, USA (2021). 10.1145\/3474085.3475369","DOI":"10.1145\/3474085.3475369"},{"key":"1761_CR40","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: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 1624\u20131633","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"1761_CR41","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. CoRR abs\/2208.08608","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"1761_CR42","doi-asserted-by":"publisher","unstructured":"Yan S, Dong N, Zhang L, Tang J (2023) Clip-driven fine-grained text-image person re-identification. IEEE Trans Image Process 32:6032\u20136046. https:\/\/doi.org\/10.1109\/TIP.2023.3327924","DOI":"10.1109\/TIP.2023.3327924"},{"key":"1761_CR43","doi-asserted-by":"publisher","unstructured":"He S, Luo H, Jiang W, Jiang X, Ding H (2024) Vgsg: vision-guided semantic-group network for text-based person search. IEEE Trans Image Process 33:163\u2013176. https:\/\/doi.org\/10.1109\/TIP.2023.3337653","DOI":"10.1109\/TIP.2023.3337653"},{"key":"1761_CR44","doi-asserted-by":"publisher","unstructured":"Yang S, Zhou Y, Zheng Z, Wang Y, Zhu L, Wu Y (2023) Towards unified text-based person retrieval: a large-scale multi-attribute and language search benchmark. In: Proceedings of the 31st ACM international conference on multimedia. MM \u201923, pp 4492\u20134501. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3581783.3611709","DOI":"10.1145\/3581783.3611709"},{"key":"1761_CR45","doi-asserted-by":"crossref","unstructured":"Bai, Y., Cao, M., Gao, D., Cao, Z., Chen, C., Fan, Z., Nie, L., Zhang, M.: Rasa: Relation and sensitivity aware representation learning for text-based person search. In: Elkind, E. (ed.) Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, pp. 555\u2013563. International Joint Conferences on Artificial Intelligence Organization, Macau, SAR, China (2023). 10.24963\/ijcai.2023\/62 . Main Track","DOI":"10.24963\/ijcai.2023\/62"},{"key":"1761_CR46","doi-asserted-by":"publisher","unstructured":"Qin Y, Chen Y, Peng D, Peng X, Zhou JT, Hu P (2024) Noisy-correspondence learning for text-to-image person re-identification. In: 2024 IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 27187\u201327196. https:\/\/doi.org\/10.1109\/CVPR52733.2024.02568","DOI":"10.1109\/CVPR52733.2024.02568"},{"issue":"1","key":"1761_CR47","doi-asserted-by":"publisher","first-page":"013018","DOI":"10.1117\/1.JEI.34.1.013018","volume":"34","author":"X Yang","year":"2025","unstructured":"Yang X, Wang J, Sun Y, Duan X (2025) CMLFA: cross-modal latent feature aligning for text-to-image person re-identification. J Electron Imaging 34(1):013018\u2013013018","journal-title":"J Electron Imaging"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01761-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-026-01761-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-026-01761-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T11:24:31Z","timestamp":1790076271000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-026-01761-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["1761"],"URL":"https:\/\/doi.org\/10.1007\/s10044-026-01761-5","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]},"assertion":[{"value":"1 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"176"}}