{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T03:52:17Z","timestamp":1784519537167,"version":"3.55.0"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2095"],"award-info":[{"award-number":["U22A2095"]}],"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":["62076258"],"award-info":[{"award-number":["62076258"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113705","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T06:52:25Z","timestamp":1776754345000},"page":"113705","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"PC","title":["A training-free framework for text-to-image person re-identification via query-prototype matching"],"prefix":"10.1016","volume":"179","author":[{"given":"Hao","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian-Fang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3883-2024","authenticated-orcid":false,"given":"Jianhuang","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113705_b1","doi-asserted-by":"crossref","unstructured":"S. Li, T. Xiao, H. Li, B. Zhou, D. Yue, X. Wang, Person search with natural language description, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1970\u20131979.","DOI":"10.1109\/CVPR.2017.551"},{"key":"10.1016\/j.patcog.2026.113705_b2","doi-asserted-by":"crossref","unstructured":"X. Han, S. He, L. Zhang, T. Xiang, Text-Based Person Search with Limited Data, in: Proceedings of the British Machine Vision Conference, BMVC, 2021.","DOI":"10.5244\/C.35.10"},{"key":"10.1016\/j.patcog.2026.113705_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110253","article-title":"Text-based person search via local-relational-global fine grained alignment","volume":"262","author":"Zhou","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.patcog.2026.113705_b4","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113705_b5","series-title":"Advances in Neural Information Processing Systems","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"Vol. 34","author":"Li","year":"2021"},{"key":"10.1016\/j.patcog.2026.113705_b6","doi-asserted-by":"crossref","unstructured":"S. Li, T. Xiao, H. Li, W. Yang, X. Wang, Identity-aware textual-visual matching with latent co-attention, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 1890\u20131899.","DOI":"10.1109\/ICCV.2017.209"},{"key":"10.1016\/j.patcog.2026.113705_b7","series-title":"International Conference on Machine Learning","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"issue":"140","key":"10.1016\/j.patcog.2026.113705_b8","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113705_b9","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.113705_b10","doi-asserted-by":"crossref","unstructured":"S. Parashar, Z. Lin, T. Liu, X. Dong, Y. Li, D. Ramanan, J. Caverlee, S. Kong, The neglected tails in vision-language models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 12988\u201312997.","DOI":"10.1109\/CVPR52733.2024.01234"},{"key":"10.1016\/j.patcog.2026.113705_b11","series-title":"Understanding and Fixing the Modality Gap in Vision-Language Models","author":"Udandarao","year":"2022"},{"key":"10.1016\/j.patcog.2026.113705_b12","unstructured":"S. Schrodi, D.T. Hoffmann, M. Argus, V. Fischer, T. Brox, Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision\u2013Language Models, in: International Conference on Learning Representations, ICLR, 2025."},{"key":"10.1016\/j.patcog.2026.113705_b13","series-title":"Advances in Neural Information Processing Systems","first-page":"84298","article-title":"Interpreting clip with sparse linear concept embeddings (splice)","volume":"Vol. 37","author":"Bhalla","year":"2024"},{"key":"10.1016\/j.patcog.2026.113705_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111247","article-title":"Local-enhanced representation for text-based person search","volume":"161","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"issue":"c","key":"10.1016\/j.patcog.2026.113705_b15","article-title":"Similarity-guided interaction and mismatched feature emphasis network for text-to-image person re-identification","volume":"667","author":"Ran","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.113705_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2026.132885","article-title":"DiCo: Disentangled concept representation for text-to-image person re-identification","author":"Kim","year":"2026","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.113705_b17","article-title":"TP-LReID: Lifelong person re-identification using text prompts","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113705_b18","article-title":"Minimizing the pretraining gap: Domain-aligned text-based person retrieval","author":"Yang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113705_b19","doi-asserted-by":"crossref","unstructured":"J. Zuo, H. Zhou, Y. Nie, F. Zhang, T. Guo, N. Sang, Y. Wang, C. Gao, Ufinebench: Towards text-based person retrieval with ultra-fine granularity, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 22010\u201322019.","DOI":"10.1109\/CVPR52733.2024.02078"},{"key":"10.1016\/j.patcog.2026.113705_b20","doi-asserted-by":"crossref","unstructured":"Y. Bai, M. Cao, D. Gao, Z. Cao, C. Chen, Z. Fan, L. Nie, M. Zhang, RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search, in: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023, pp. 555\u2013563.","DOI":"10.24963\/ijcai.2023\/62"},{"key":"10.1016\/j.patcog.2026.113705_b21","doi-asserted-by":"crossref","unstructured":"S. Yang, Y. Zhou, Z. Zheng, Y. Wang, L. Zhu, Y. Wu, 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, 2023, pp. 4492\u20134501.","DOI":"10.1145\/3581783.3611709"},{"issue":"10","key":"10.1016\/j.patcog.2026.113705_b22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3721482","article-title":"MARS: Paying more attention to visual attributes for text-based person search","volume":"21","author":"Ergasti","year":"2025","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.patcog.2026.113705_b23","doi-asserted-by":"crossref","unstructured":"D. Jiang, M. Ye, 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, 2023, pp. 2787\u20132797.","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"10.1016\/j.patcog.2026.113705_b24","doi-asserted-by":"crossref","unstructured":"Y. Qin, Y. Chen, D. Peng, X. Peng, J.T. Zhou, P. Hu, Noisy-correspondence learning for text-to-image person re-identification, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 27197\u201327206.","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"10.1016\/j.patcog.2026.113705_b25","doi-asserted-by":"crossref","unstructured":"S. Li, C. He, X. Xu, F. Shen, Y. Yang, H.T. Shen, Adaptive uncertainty-based learning for text-based person retrieval, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 3172\u20133180.","DOI":"10.1609\/aaai.v38i4.28101"},{"key":"10.1016\/j.patcog.2026.113705_b26","doi-asserted-by":"crossref","unstructured":"S. Yan, J. Liu, N. Dong, L. Zhang, J. Tang, Prototypical Prompting for Text-to-image Person Re-identification, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 2331\u20132340.","DOI":"10.1145\/3664647.3681165"},{"key":"10.1016\/j.patcog.2026.113705_b27","series-title":"European Conference on Computer Vision","first-page":"474","article-title":"PLOT: Text-based person search with part slot attention for corresponding part discovery","author":"Park","year":"2024"},{"key":"10.1016\/j.patcog.2026.113705_b28","doi-asserted-by":"crossref","unstructured":"J. Jiang, C. Ding, W. Tan, J. Wang, J. Tao, X. Xu, Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2025.","DOI":"10.1109\/CVPR52734.2025.00861"},{"issue":"1","key":"10.1016\/j.patcog.2026.113705_b29","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1109\/TPAMI.2008.285","article-title":"Accurate image search using the contextual dissimilarity measure","volume":"32","author":"Jegou","year":"2008","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113705_b30","series-title":"2007 IEEE 11th International Conference on Computer Vision","first-page":"1","article-title":"Total recall: Automatic query expansion with a generative feature model for object retrieval","author":"Chum","year":"2007"},{"key":"10.1016\/j.patcog.2026.113705_b31","series-title":"2012 19th IEEE International Conference on Image Processing","first-page":"1621","article-title":"Common-near-neighbor analysis for person re-identification","author":"Li","year":"2012"},{"issue":"3","key":"10.1016\/j.patcog.2026.113705_b32","doi-asserted-by":"crossref","DOI":"10.1177\/15501477211066305","article-title":"Re-ranking vehicle re-identification with orientation-guide query expansion","volume":"18","author":"Zhang","year":"2022","journal-title":"Int. J. Distrib. Sens. Netw."},{"key":"10.1016\/j.patcog.2026.113705_b33","doi-asserted-by":"crossref","first-page":"131352","DOI":"10.1109\/ACCESS.2020.3009653","article-title":"RRGCCAN: Re-ranking via graph convolution channel attention network for person re-identification","volume":"8","author":"Chen","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.patcog.2026.113705_b34","doi-asserted-by":"crossref","unstructured":"Z. Zhong, L. Zheng, D. Cao, S. Li, Re-ranking person re-identification with k-reciprocal encoding, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1318\u20131327.","DOI":"10.1109\/CVPR.2017.389"},{"key":"10.1016\/j.patcog.2026.113705_b35","doi-asserted-by":"crossref","unstructured":"M.S. Sarfraz, A. Schumann, A. Eberle, R. Stiefelhagen, A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 420\u2013429.","DOI":"10.1109\/CVPR.2018.00051"},{"key":"10.1016\/j.patcog.2026.113705_b36","series-title":"Density estimation for statistics and data analysis","author":"Dehnad","year":"1987"},{"key":"10.1016\/j.patcog.2026.113705_b37","series-title":"Semantically self-aligned network for text-to-image part-aware person re-identification (2021)","author":"Ding","year":"2021"},{"key":"10.1016\/j.patcog.2026.113705_b38","doi-asserted-by":"crossref","unstructured":"A. Zhu, Z. Wang, Y. Li, X. Wan, J. Jin, T. Wang, F. Hu, G. Hua, Dssl: Deep surroundings-person separation learning for text-based person retrieval, in: Proceedings of the 29th ACM International Conference on Multimedia, 2021, pp. 209\u2013217.","DOI":"10.1145\/3474085.3475369"},{"key":"10.1016\/j.patcog.2026.113705_b39","doi-asserted-by":"crossref","unstructured":"S. Paisitkriangkrai, C. Shen, A. Van Den Hengel, Learning to rank in person re-identification with metric ensembles, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1846\u20131855.","DOI":"10.1109\/CVPR.2015.7298794"},{"key":"10.1016\/j.patcog.2026.113705_b40","doi-asserted-by":"crossref","unstructured":"L. Zheng, L. Shen, L. Tian, S. Wang, J. Wang, Q. Tian, Scalable person re-identification: A benchmark, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1116\u20131124.","DOI":"10.1109\/ICCV.2015.133"},{"key":"10.1016\/j.patcog.2026.113705_b41","unstructured":"J.B. McQueen, Some methods of classification and analysis of multivariate observations, in: Proc. of 5th Berkeley Symposium on Math. Stat. and Prob., 1967, pp. 281\u2013297."},{"key":"10.1016\/j.patcog.2026.113705_b42","doi-asserted-by":"crossref","unstructured":"M. Cao, Y. Bai, Z. Zeng, M. Ye, M. Zhang, An empirical study of clip for text-based person search, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 465\u2013473.","DOI":"10.1609\/aaai.v38i1.27801"},{"key":"10.1016\/j.patcog.2026.113705_b43","doi-asserted-by":"crossref","unstructured":"Z. Zhao, B. Liu, Y. Lu, Q. Chu, N. Yu, Unifying multi-modal uncertainty modeling and semantic alignment for text-to-image person re-identification, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 7534\u20137542.","DOI":"10.1609\/aaai.v38i7.28585"},{"key":"10.1016\/j.patcog.2026.113705_b44","article-title":"Learning semantic polymorphic mapping for text-based person retrieval","author":"Li","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113705_b45","doi-asserted-by":"crossref","unstructured":"Y. Liu, G. Qin, H. Chen, Z. Cheng, X. Yang, Causality-inspired invariant representation learning for text-based person retrieval, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 14052\u201314060.","DOI":"10.1609\/aaai.v38i12.29314"},{"key":"10.1016\/j.patcog.2026.113705_b46","doi-asserted-by":"crossref","unstructured":"F. Yang, W. Li, M. Yang, B. Liang, J. Zhang, Multi-modal disordered representation learning network for description-based person search, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 16316\u201316324.","DOI":"10.1609\/aaai.v38i15.29567"},{"key":"10.1016\/j.patcog.2026.113705_b47","doi-asserted-by":"crossref","unstructured":"D. Wang, F. Yan, Y. Wang, L. Zhao, X. Liang, H. Zhong, R. Zhang, Fine-grained Semantics-aware Representation Learning for Text-based Person Retrieval, in: Proceedings of the 2024 International Conference on Multimedia Retrieval, 2024, pp. 92\u2013100.","DOI":"10.1145\/3652583.3658054"},{"key":"10.1016\/j.patcog.2026.113705_b48","doi-asserted-by":"crossref","unstructured":"Y. Wang, M. Yang, R. Cao, Fine-grained Semantic Alignment with Transferred Person-SAM for Text-based Person Retrieval, in: Proceedings of the 32nd ACM International Conference on Multimedia, 2024, pp. 5432\u20135441.","DOI":"10.1145\/3664647.3681553"},{"issue":"1","key":"10.1016\/j.patcog.2026.113705_b49","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"10.1016\/j.patcog.2026.113705_b50","series-title":"Kdd","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","volume":"Vol. 96","author":"Ester","year":"1996"},{"key":"10.1016\/j.patcog.2026.113705_b51","doi-asserted-by":"crossref","unstructured":"F. Yang, R. Hinami, Y. Matsui, S. Ly, S. Satoh, Efficient image retrieval via decoupling diffusion into online and offline processing, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 2019, pp. 9087\u20139094.","DOI":"10.1609\/aaai.v33i01.33019087"},{"key":"10.1016\/j.patcog.2026.113705_b52","unstructured":"G. Lample, A. Conneau, M. Ranzato, L. Denoyer, H. J\u00e9gou, Word translation without parallel data, in: International Conference on Learning Representations, 2018."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006709?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006709?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T08:32:29Z","timestamp":1784277149000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":52,"alternative-id":["S0031320326006709"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113705","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A training-free framework for text-to-image person re-identification via query-prototype matching","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113705","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113705"}}