{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T10:45:06Z","timestamp":1777632306018,"version":"3.51.4"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Jiangsu Province Natural Science Foundation","doi-asserted-by":"publisher","award":["BK20220107"],"award-info":[{"award-number":["BK20220107"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003524","name":"Ministry of Business, Innovation and Employment","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003524","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92470202"],"award-info":[{"award-number":["92470202"]}],"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":["U20B2065"],"award-info":[{"award-number":["U20B2065"]}],"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":["62172231"],"award-info":[{"award-number":["62172231"]}],"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":[[2025,5]]},"DOI":"10.1016\/j.patcog.2024.111247","type":"journal-article","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T17:31:24Z","timestamp":1733419884000},"page":"111247","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":17,"special_numbering":"C","title":["Local-enhanced representation for text-based person search"],"prefix":"10.1016","volume":"161","author":[{"given":"Guoqing","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6518-8890","authenticated-orcid":false,"given":"Yuhao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yuhui","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Gaven","family":"Martin","sequence":"additional","affiliation":[]},{"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2024.111247_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109743","article-title":"SMPR: Single-stage multi-person pose regression","volume":"143","author":"Miao","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.111247_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109891","article-title":"Motional foreground attention-based video crowd counting","volume":"144","author":"Ling","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2024.111247_b3","doi-asserted-by":"crossref","first-page":"4555","DOI":"10.1109\/TIP.2023.3279673","article-title":"Multi-biometric unified network for cloth-changing person re-identification","volume":"32","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"10.1016\/j.patcog.2024.111247_b4","doi-asserted-by":"crossref","first-page":"4096","DOI":"10.1109\/TCSVT.2023.3240001","article-title":"Camera contrast learning for unsupervised person re-identification","volume":"33","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2024.111247_b5","doi-asserted-by":"crossref","unstructured":"Y. Li, J. He, T. Zhang, X. Liu, Y. Zhang, F. Wu, Diverse part discovery: Occluded person re-identification with part-aware transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 2898\u20132907.","DOI":"10.1109\/CVPR46437.2021.00292"},{"key":"10.1016\/j.patcog.2024.111247_b6","doi-asserted-by":"crossref","first-page":"8913","DOI":"10.1109\/TIP.2021.3120054","article-title":"Deep high-resolution representation learning for cross-resolution person re-identification","volume":"30","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"issue":"10","key":"10.1016\/j.patcog.2024.111247_b7","doi-asserted-by":"crossref","first-page":"6766","DOI":"10.1109\/TCSVT.2022.3169422","article-title":"Illumination unification for person re-identification","volume":"32","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2024.111247_b8","doi-asserted-by":"crossref","unstructured":"V.D. Nguyen, P. Mantini, S.K. Shah, Contrastive Clothing and Pose Generation for Cloth-Changing Person Re-Identification, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 7541\u20137549.","DOI":"10.1109\/CVPRW63382.2024.00749"},{"key":"10.1016\/j.patcog.2024.111247_b9","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.neucom.2022.04.081","article-title":"Tipcb: A simple but effective part-based convolutional baseline for text-based person search","volume":"494","author":"Chen","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2024.111247_b10","doi-asserted-by":"crossref","unstructured":"S. Aggarwal, V.B. Radhakrishnan, A. Chakraborty, Text-based person search via attribute-aided matching, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2020, pp. 2617\u20132625.","DOI":"10.1109\/WACV45572.2020.9093640"},{"key":"10.1016\/j.patcog.2024.111247_b11","doi-asserted-by":"crossref","unstructured":"Z. Wang, Z. Fang, J. Wang, Y. Yang, Vitaa: Visual-textual attributes alignment in person search by natural language, in: Proceedings of the European Conference on Computer Vision, ECCV, 2020, pp. 402\u2013420.","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"10.1016\/j.patcog.2024.111247_b12","doi-asserted-by":"crossref","unstructured":"Y. Jing, C. Si, J. Wang, W. Wang, L. Wang, T. Tan, Pose-guided multi-granularity attention network for text-based person search, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2020, pp. 11189\u201311196.","DOI":"10.1609\/aaai.v34i07.6777"},{"key":"10.1016\/j.patcog.2024.111247_b13","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.2024.111247_b14","doi-asserted-by":"crossref","unstructured":"A. Farooq, M. Awais, J. Kittler, S.S. Khalid, Axm-net: Implicit cross-modal feature alignment for person re-identification, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2022, pp. 4477\u20134485.","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"10.1016\/j.patcog.2024.111247_b15","doi-asserted-by":"crossref","unstructured":"Y. Zhang, H. Lu, Deep cross-modal projection learning for image-text matching, in: Proceedings of the European Conference on Computer Vision, ECCV, 2018, pp. 686\u2013701.","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"10.1016\/j.patcog.2024.111247_b16","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.2024.111247_b17","series-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"10.1016\/j.patcog.2024.111247_b18","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.2024.111247_b19","doi-asserted-by":"crossref","unstructured":"J. Gu, J. Cai, S.R. Joty, L. Niu, G. Wang, Look, imagine and match: Improving textual-visual cross-modal retrieval with generative models, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7181\u20137189.","DOI":"10.1109\/CVPR.2018.00750"},{"key":"10.1016\/j.patcog.2024.111247_b20","doi-asserted-by":"crossref","unstructured":"C. Liu, Z. Mao, T. Zhang, H. Xie, B. Wang, Y. Zhang, Graph structured network for image-text matching, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Pecognition, 2020, pp. 10921\u201310930.","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"10.1016\/j.patcog.2024.111247_b21","doi-asserted-by":"crossref","first-page":"8037","DOI":"10.1109\/TCSVT.2022.3182426","article-title":"Dual-level representation enhancement on characteristic and context for image-text retrieval","volume":"32","author":"Yang","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2024.111247_b22","doi-asserted-by":"crossref","unstructured":"Z. Wang, A. Zhu, J. Xue, X. Wan, C. Liu, T. Wang, Y. Li, Caibc: Capturing all-round information beyond color for text-based person retrieval, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 5314\u20135322.","DOI":"10.1145\/3503161.3548057"},{"key":"10.1016\/j.patcog.2024.111247_b23","doi-asserted-by":"crossref","unstructured":"X. Shu, W. Wen, H. Wu, K. Chen, Y. Song, R. Qiao, B. Ren, C. Wang, See finer, see more: Implicit modality alignment for text-based person retrieval, in: European Conference on Computer Vision, 2022, pp. 624\u2013641.","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"10.1016\/j.patcog.2024.111247_b24","doi-asserted-by":"crossref","first-page":"5542","DOI":"10.1109\/TIP.2020.2984883","article-title":"Improving description-based person re-identification by multi-granularity image-text alignments","author":"Niu","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2024.111247_b25","doi-asserted-by":"crossref","unstructured":"N. Sarafianos, X. Xu, I.A. Kakadiaris, Adversarial representation learning for text-to-image matching, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 5814\u20135824.","DOI":"10.1109\/ICCV.2019.00591"},{"key":"10.1016\/j.patcog.2024.111247_b26","first-page":"8922","article-title":"Pedestrian-specific bipartite-aware similarity learning for text-based person retrieval","author":"Shen","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2024.111247_b27","doi-asserted-by":"crossref","unstructured":"Z. Shao, X. Zhang, M. Fang, Z. Lin, J. Wang, C. Ding, Learning granularity-unified representations for text-to-image person re-identification, in: Proceedings of the 30th ACM International Conference on Multimedia, 2022, pp. 5566\u20135574.","DOI":"10.1145\/3503161.3548028"},{"key":"10.1016\/j.patcog.2024.111247_b28","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.patcog.2024.111247_b29","unstructured":"K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, in: 3rd International Conference on Learning Representations, ICLR, 2015."},{"key":"10.1016\/j.patcog.2024.111247_b30","unstructured":"J. Chung, C. Gulcehre, K. Cho, Y. Bengio, Empirical evaluation of gated recurrent neural networks on sequence modeling, in: NIPS 2014 Workshop on Deep Learning, 2014."},{"issue":"8","key":"10.1016\/j.patcog.2024.111247_b31","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"10.1016\/j.patcog.2024.111247_b32","doi-asserted-by":"crossref","unstructured":"J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding, in: Proceedings of NAACL-HLT, 2019, pp. 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.1016\/j.patcog.2024.111247_b33","doi-asserted-by":"crossref","unstructured":"C. Wang, Z. Luo, Y. Lin, S. Li, Text-based Person Search via Multi-Granularity Embedding Learning, in: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021, pp. 1068\u20131074.","DOI":"10.24963\/ijcai.2021\/148"},{"key":"10.1016\/j.patcog.2024.111247_b34","doi-asserted-by":"crossref","unstructured":"Z. Wang, A. Zhu, J. Xue, X. Wan, C. Liu, T. Wang, Y. Li, 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, 2022, pp. 1984\u20131992.","DOI":"10.1145\/3503161.3548166"},{"key":"10.1016\/j.patcog.2024.111247_b35","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2023.3273719","article-title":"Addressing information inequality for text-based person search via pedestrian-centric visual denoising and bias-aware alignments","author":"Gao","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2024.111247_b36","doi-asserted-by":"crossref","first-page":"1990","DOI":"10.1109\/TIP.2024.3372832","article-title":"Comprehensive attribute prediction learning for person search by language","volume":"33","author":"Niu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"10.1016\/j.patcog.2024.111247_b37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3383184","article-title":"Dual-path convolutional image-text embeddings with instance loss","volume":"16","author":"Zheng","year":"2020","journal-title":"ACM Trans. Multimed. Comput. Commun Appl. (TOMM)"},{"key":"10.1016\/j.patcog.2024.111247_b38","first-page":"1","article-title":"Image-specific information suppression and implicit local alignment for text-based person search","author":"Yan","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2024.111247_b39","doi-asserted-by":"crossref","first-page":"3429","DOI":"10.1109\/TIP.2023.3285426","article-title":"Improving inconspicuous attributes modeling for person search by language","volume":"32","author":"Niu","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2024.111247_b40","doi-asserted-by":"crossref","unstructured":"Z. Wang, J. Xue, A. Zhu, Y. Li, M. Zhang, C. Zhong, Amen: Adversarial multi-space embedding network for text-based person re-identification, in: Pattern Recognition and Computer Vision: 4th Chinese Conference, 2021, pp. 462\u2013473.","DOI":"10.1007\/978-3-030-88007-1_38"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320324009981?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320324009981?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:56:13Z","timestamp":1777434973000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320324009981"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":40,"alternative-id":["S0031320324009981"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2024.111247","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2025,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Local-enhanced representation for text-based person search","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2024.111247","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"111247"}}