{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T13:13:13Z","timestamp":1783948393998,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819697939","type":"print"},{"value":"9789819697946","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-9794-6_33","type":"book-chapter","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T06:13:04Z","timestamp":1752473584000},"page":"393-405","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CLIO: A Unified Framework for Consistency-Aware Learning and Intra-Modal Optimization in Text-Based Person Re-identification"],"prefix":"10.1007","author":[{"given":"Xinpan","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaomin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guihu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liujie","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenguang","family":"Gan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiabao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"33_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102879","volume":"118","author":"F Jiang","year":"2025","unstructured":"Jiang, F., Yang, S., Jones, M.W., et al.: From attributes to natural language: a survey and foresight on text-based person re-identification. Inf. Fusion 118, 102879 (2025)","journal-title":"Inf. Fusion"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Jiang, D., Ye, M.: Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2787\u20132797 (2023)","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"33_CR3","doi-asserted-by":"publisher","first-page":"6032","DOI":"10.1109\/TIP.2023.3327924","volume":"32","author":"S Yan","year":"2023","unstructured":"Yan, S., Dong, N., Zhang, L., et al.: Clip-driven fine-grained text-image person re-identification. IEEE Trans. Image Process. 32, 6032\u20136046 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR4","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning. PMLR, pp. 8748\u20138763 (2021)"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., et al.: Person search with natural language description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1970\u20131979 (2017)","DOI":"10.1109\/CVPR.2017.551"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhang, X., Fang, M., et al.: Learning granularity-unified representations for text-to-image person re-identification. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5566\u20135574 (2022)","DOI":"10.1145\/3503161.3548028"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Shu, X., Wen, W., Wu, H., et al.: See finer, see more: implicit modality alignment for text-based person retrieval. In: European Conference on Computer Vision, 624\u2013641. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhu, A., Xue, J., et al.: Look before you leap: improving text-based person retrieval by learning a consistent cross-modal common manifold. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1984\u20131992 (2022)","DOI":"10.1145\/3503161.3548166"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zheng, L., Garrett, M., et al.: Dual-path convolutional image-text embeddings with instance loss. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 16(2), 1\u201323 (2020)","DOI":"10.1145\/3383184"},{"key":"33_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104222","volume":"250","author":"Y Wei","year":"2025","unstructured":"Wei, Y., Zhang, Y., Li, K., et al.: Leveraging vision-language prompts for real-world image restoration and enhancement. Comput. Vis. Image Underst. 250, 104222 (2025)","journal-title":"Comput. Vis. Image Underst."},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Wang, Z., Fang, Z., Wang, J., et al.: VITAA: visual-textual attributes alignment in person search by natural language. In: Computer Vision\u2013ECCV 2020, vol. 16, pp. 402\u2013420 (2020)","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Zhu, A., Wang, Z., Li, Y., et al.: DSSL: deep surroundings-person separation learning for text-based person retrieval. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 209\u2013217 (2021)","DOI":"10.1145\/3474085.3475369"},{"key":"33_CR13","unstructured":"Ding, Z., Ding, C., Shao, Z., et al.: Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv preprint arXiv:2107.12666 (2021)"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yan, Z., Han, X., et al.: LapsCore: language-guided person search via color reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1624\u20131633 (2021)","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Han, X., He, S., Zhang, L., et al.: Text-based person search with limited data. arXiv preprint arXiv:2110.10807 (2021)","DOI":"10.5244\/C.35.10"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Cao, M., Zhang, M.: Learning semantic-aligned feature representation for text-based person search. In: ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 2724\u20132728. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746846"},{"key":"33_CR17","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.neucom.2022.04.081","volume":"494","author":"Y Chen","year":"2022","unstructured":"Chen, Y., Zhang, G., Lu, Y., et al.: TIPCB: a simple but effective part-based convolutional baseline for text-based person search. Neurocomputing 494, 171\u2013181 (2022)","journal-title":"Neurocomputing"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhu, A., Xue, J., et al.: Caibc: capturing all-round information beyond color for text-based person retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5314\u20135322 (2022)","DOI":"10.1145\/3503161.3548057"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Farooq, A., Awais, M., Kittler, J., et al.: AXM-Net: implicit cross-modal feature alignment for person re-identification. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 36(4), pp. 4477\u20134485 (2022)","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"33_CR20","unstructured":"Zheng, Y., Zhao, X., Lan, C., et al.: CPCL: cross-modal prototypical contrastive learning for weakly supervised text-based person re-identification. arXiv preprint arXiv:2401.10011 (2024)"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Zuo, J., Zhou, H., Nie, Y., et al.: Ufinebench: towards text-based person retrieval with ultra-fine granularity. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22010\u201322019 (2024)","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 686\u2013701 (2018)","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Shu, X., Wen, W., Wu, H., et al.: See finer, see more: implicit modality alignment for text-based person retrieval. In: European Conference on Computer Vision, pp. 624\u2013641. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-25072-9_42"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9794-6_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T12:42:58Z","timestamp":1783946578000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9794-6_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819697939","9789819697946"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9794-6_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"15 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}