{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T14:22:25Z","timestamp":1791814945601,"version":"4.3.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031533044","type":"print"},{"value":"9783031533051","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53305-1_16","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"201-215","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Cross-Modal Semantic Alignment Learning for\u00a0Text-Based Person Search"],"prefix":"10.1007","author":[{"given":"Wenjun","family":"Gan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangchun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guozhi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"16_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-030-01270-0_4","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Chen","year":"2018","unstructured":"Chen, D., et al.: Improving deep visual representation for person re-identification by global and local image-language association. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 56\u201373. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_4"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Salience-guided cascaded suppression network for person re-identification. In: CVPR, pp. 3300\u20133310 (2020)","DOI":"10.1109\/CVPR42600.2020.00336"},{"key":"16_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal Image-TExt Representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"16_CR4","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., Wang, Z., Zheng, Y.: TIPCB: a simple but effective part-based convolutional baseline for text-based person search. Neurocomputing 494, 171\u2013181 (2022)","journal-title":"Neurocomputing"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, G., Zhang, H., Zheng, Y., Lin, W.: Multi-level part-aware feature disentangling for text-based person search. In: ICME, pp. 2801\u20132806 (2023)","DOI":"10.1109\/ICME55011.2023.00476"},{"key":"16_CR6","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Advances in Neural Information Processing Systems, vol. 26 (2013)"},{"key":"16_CR7","unstructured":"Ding, Z., Ding, C., Shao, Z., Tao, D.: Semantically self-aligned network for text-to-image part-aware person re-identification. arXiv preprint arXiv:2107.12666 (2021)"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2360\u20132367 (2010)","DOI":"10.1109\/CVPR.2010.5539926"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Farooq, A., Awais, M., Kittler, J., Khalid, S.S.: AXM-Net: implicit cross-modal feature alignment for person re-identification. In: AAAI, pp. 4477\u20134485 (2022)","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"16_CR10","unstructured":"Gao, C., et al.: Contextual non-local alignment over full-scale representation for text-based person search. arXiv preprint arXiv:2101.03036 (2021)"},{"key":"16_CR11","unstructured":"Han, X., He, S., Zhang, L., Xiang, T.: Text-based person search with limited data. arXiv preprint arXiv:2110.10807 (2021)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"He, T., Jin, X., Shen, X., Huang, J., Chen, Z., Hua, X.S.: Dense interaction learning for video-based person re-identification. In: ICCV, pp. 1490\u20131501 (2021)","DOI":"10.1109\/ICCV48922.2021.00152"},{"key":"16_CR13","unstructured":"Hermans, A., Beyer, L., Leibe, B.: In defense of the triplet loss for person re-identification. arXiv preprint arXiv:1703.07737 (2017)"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Hou, R., Ma, B., Chang, H., Gu, X., Shan, S., Chen, X.: Interaction-and-aggregation network for person re-identification. In: CVPR, pp. 9317\u20139326 (2019)","DOI":"10.1109\/CVPR.2019.00954"},{"key":"16_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/978-3-030-01234-2_22","volume-title":"Computer Vision \u2013 ECCV 2018","author":"V Jampani","year":"2018","unstructured":"Jampani, V., Sun, D., Liu, M.-Y., Yang, M.-H., Kautz, J.: Superpixel sampling networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 363\u2013380. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_22"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Jing, Y., Si, C., Wang, J., Wang, W., Wang, L., Tan, T.: Pose-guided multi-granularity attention network for text-based person search. In: AAAI, pp. 11189\u201311196 (2020)","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"16_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"16_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1007\/978-3-030-01225-0_13","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K-H Lee","year":"2018","unstructured":"Lee, K.-H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 212\u2013228. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_13"},{"key":"16_CR19","doi-asserted-by":"publisher","first-page":"2238","DOI":"10.1109\/LSP.2022.3217682","volume":"29","author":"S Li","year":"2022","unstructured":"Li, S., Lu, A., Huang, Y., Li, C., Wang, L.: Joint token and feature alignment framework for text-based person search. IEEE Signal Process. Lett. 29, 2238\u20132242 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Li, S., Xiao, T., Li, H., Zhou, B., Yue, D., Wang, X.: Person search with natural language description. In: CVPR, pp. 1970\u20131979 (2017)","DOI":"10.1109\/CVPR.2017.551"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Liu, J., Zha, Z.J., Hong, R., Wang, M., Zhang, Y.: Deep adversarial graph attention convolution network for text-based person search. In: ACM MM, pp. 665\u2013673 (2019)","DOI":"10.1145\/3343031.3350991"},{"key":"16_CR22","doi-asserted-by":"publisher","first-page":"5542","DOI":"10.1109\/TIP.2020.2984883","volume":"29","author":"K Niu","year":"2020","unstructured":"Niu, K., Huang, Y., Ouyang, W., Wang, L.: Improving description-based person re-identification by multi-granularity image-text alignments. IEEE Trans. Image Process. 29, 5542\u20135556 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"16_CR23","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909 (2015)","DOI":"10.18653\/v1\/P16-1162"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhang, X., Fang, M., Lin, Z., Wang, J., Ding, C.: Learning granularity-unified representations for text-to-image person re-identification. In: ACM MM, pp. 5566\u20135574 (2022)","DOI":"10.1145\/3503161.3548028"},{"key":"16_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1007\/978-3-030-01267-0_30","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Shen","year":"2018","unstructured":"Shen, Y., Li, H., Yi, S., Chen, D., Wang, X.: Person re-identification with deep similarity-guided graph neural network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 508\u2013526. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_30"},{"key":"16_CR27","doi-asserted-by":"publisher","unstructured":"Shu, X., et al.: See finer, see more: implicit modality alignment for text-based person retrieval. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision \u2013 ECCV 2022 Workshops. ECCV 2022. LNCS, vol. 13805, pp. 624\u2013641. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25072-9_42","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Wang, C., Luo, Z., Lin, Y., Li, S.: Text-based person search via multi-granularity embedding learning. In: IJCAI, pp. 1068\u20131074 (2021)","DOI":"10.24963\/ijcai.2021\/148"},{"key":"16_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/978-3-030-58610-2_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Fang, Z., Wang, J., Yang, Y.: ViTAA: visual-textual attributes alignment in person search by natural language. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 402\u2013420. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_24"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CAIBC: capturing all-round information beyond color for text-based person retrieval. In: ACM MM, pp. 5314\u20135322 (2022)","DOI":"10.1145\/3503161.3548057"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Look before you leap: improving text-based person retrieval by learning a consistent cross-modal common manifold. In: ACM MM, pp. 1984\u20131992 (2022)","DOI":"10.1145\/3503161.3548166"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Wei, L., Zhang, S., Gao, W., Tian, Q.: Person transfer GAN to bridge domain gap for person re-identification. In: CVPR, pp. 79\u201388 (2018)","DOI":"10.1109\/CVPR.2018.00016"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Wu, B., Cheng, R., Zhang, P., Vajda, P., Gonzalez, J.E.: Data efficient language-supervised zero-shot recognition with optimal transport distillation. arXiv preprint arXiv:2112.09445 (2021)","DOI":"10.1109\/CVPRW53098.2021.00348"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yan, Z., Han, X., Li, G., Zou, C., Cui, S.: LapsCore: language-guided person search via color reasoning. In: ICCV, pp. 1624\u20131633 (2021)","DOI":"10.1109\/ICCV48922.2021.00165"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Yan, S., Dong, N., Zhang, L., Tang, J.: Clip-driven fine-grained text-image person re-identification. arXiv preprint arXiv:2210.10276 (2022)","DOI":"10.1109\/TIP.2023.3327924"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, D., Zha, Z.J.: Improving triplet-wise training of convolutional neural network for vehicle re-identification. In: ICME, pp. 1386\u20131391 (2017)","DOI":"10.1109\/ICME.2017.8019491"},{"key":"16_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/978-3-030-01246-5_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Zhang","year":"2018","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 707\u2013723. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_42"},{"key":"16_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, K., Liu, W., He, L., Mei, T., Luo, J., Zha, Z.J.: Group-aware label transfer for domain adaptive person re-identification. In: CVPR, pp. 5310\u20135319 (2021)","DOI":"10.1109\/CVPR46437.2021.00527"},{"key":"16_CR39","doi-asserted-by":"crossref","unstructured":"Zheng, K., Liu, W., Liu, J., Zha, Z.J., Mei, T.: Hierarchical Gumbel attention network for text-based person search. In: ACM MM, pp. 3441\u20133449 (2020)","DOI":"10.1145\/3394171.3413864"},{"key":"16_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3383184","volume":"16","author":"Z Zheng","year":"2020","unstructured":"Zheng, Z., Zheng, L., Garrett, M., Yang, Y., Xu, M., Shen, Y.D.: Dual-path convolutional image-text embeddings with instance loss. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 16, 1\u201323 (2020)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl. (TOMM)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53305-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:59:42Z","timestamp":1710331182000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53305-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533044","9783031533051"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53305-1_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"112","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}