{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T07:48:51Z","timestamp":1782719331648,"version":"3.54.5"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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","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":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114324","type":"journal-article","created":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T23:51:24Z","timestamp":1782345084000},"page":"114324","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Auto-Feedback Semantic Interface Learning for Text-Based Person Retrieval"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4009-7013","authenticated-orcid":false,"given":"Jiayi","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3826-6405","authenticated-orcid":false,"given":"Min","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5913-1069","authenticated-orcid":false,"given":"Meng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2551-4748","authenticated-orcid":false,"given":"Jun","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0692-8411","authenticated-orcid":false,"given":"Saeed","family":"Anwar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5206-3842","authenticated-orcid":false,"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114324_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111755","article-title":"A unified framework of data augmentation using large language models for text-based cross-modal retrieval","volume":"167","author":"Si","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114324_b2","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.2026.114324_b3","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.2026.114324_b4","doi-asserted-by":"crossref","unstructured":"L. Gao, K. Niu, Z. Ma, B. Jiao, T. Tan, P. Wang, Text-guided visual feature refinement for text-based person search, in: Proceedings of the 2021 International Conference on Multimedia Retrieval, 2021, pp. 118\u2013126.","DOI":"10.1145\/3460426.3463652"},{"key":"10.1016\/j.patcog.2026.114324_b5","series-title":"European Conference on Computer Vision","first-page":"624","article-title":"See finer, see more: Implicit modality alignment for text-based person retrieval","author":"Shu","year":"2022"},{"key":"10.1016\/j.patcog.2026.114324_b6","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"},{"key":"10.1016\/j.patcog.2026.114324_b7","series-title":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"2724","article-title":"Learning semantic-aligned feature representation for text-based person search","author":"Li","year":"2022"},{"key":"10.1016\/j.patcog.2026.114324_b8","doi-asserted-by":"crossref","first-page":"10678","DOI":"10.1109\/TMM.2024.3410129","article-title":"Learning semantic polymorphic mapping for text-based person retrieval","volume":"26","author":"Li","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114324_b9","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"27187","article-title":"Noisy-correspondence learning for text-to-image person re-identification","author":"Qin","year":"2024"},{"key":"10.1016\/j.patcog.2026.114324_b10","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2787","article-title":"Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval","author":"Jiang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114324_b11","series-title":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"2895","article-title":"MGRL: Mutual-guidance representation learning for text-to-image person retrieval","author":"Lv","year":"2024"},{"key":"10.1016\/j.patcog.2026.114324_b12","series-title":"Advances in Neural Information Processing Systems","first-page":"47069","article-title":"Generalizable person re-identification via balancing alignment and uniformity","volume":"Vol. 37","author":"Cho","year":"2024"},{"key":"10.1016\/j.patcog.2026.114324_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112760","article-title":"Global aggregated gradient-guided adversarial attacks for person re-identification","volume":"172","author":"Tao","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114324_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112817","article-title":"Intra-modal consistency for image-text retrieval through soft-label distillation","volume":"173","author":"Chen","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114324_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111647","article-title":"CSA: Cross-scale alignment with adaptive semantic aggregation and filter for image\u2013text retrieval","volume":"165","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114324_b16","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.2026.114324_b17","series-title":"2019 IEEE\/CVF International Conference on Computer Vision","first-page":"5813","article-title":"Adversarial representation learning for text-to-image matching","author":"Sarafianos","year":"2019"},{"key":"10.1016\/j.patcog.2026.114324_b18","doi-asserted-by":"crossref","first-page":"6097","DOI":"10.1109\/TIP.2022.3205216","article-title":"Conditional feature learning based transformer for text-based person search","volume":"31","author":"Gao","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114324_b19","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, Vol. 36, 2022, pp. 4477\u20134485.","DOI":"10.1609\/aaai.v36i4.20370"},{"key":"10.1016\/j.patcog.2026.114324_b20","series-title":"Advances in Neural Information Processing Systems","first-page":"54061","article-title":"TOA: Task-oriented active VQA","volume":"Vol. 36","author":"Xing","year":"2023"},{"key":"10.1016\/j.patcog.2026.114324_b21","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"15598","article-title":"GRAM: Global reasoning for multi-page VQA","author":"Blau","year":"2024"},{"key":"10.1016\/j.patcog.2026.114324_b22","series-title":"European Conference on Computer Vision","first-page":"95","article-title":"Rethinking data augmentation for robust visual question answering","author":"Chen","year":"2022"},{"key":"10.1016\/j.patcog.2026.114324_b23","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"6346","article-title":"Discovering the unknown knowns: Turning implicit knowledge in the dataset into explicit training examples for visual question answering","author":"Kil","year":"2021"},{"key":"10.1016\/j.patcog.2026.114324_b24","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10867","article-title":"From images to textual prompts: Zero-shot visual question answering with frozen large language models","author":"Guo","year":"2023"},{"key":"10.1016\/j.patcog.2026.114324_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110399","article-title":"Prompting large language model with context and pre-answer for knowledge-based VQA","volume":"151","author":"Hu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114324_b26","series-title":"Exploiting the textual potential from vision-language pre-training for text-based person search","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114324_b27","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.2026.114324_b28","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5187","article-title":"Person search with natural language description","author":"Li","year":"2017"},{"key":"10.1016\/j.patcog.2026.114324_b29","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.2026.114324_b30","series-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"10.1016\/j.patcog.2026.114324_b31","doi-asserted-by":"crossref","first-page":"6032","DOI":"10.1109\/TIP.2023.3327924","article-title":"CLIP-driven fine-grained text-image person re-identification","volume":"32","author":"Yan","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2026.114324_b32","series-title":"2023 IEEE\/CVF International Conference on Computer Vision Workshops","first-page":"2778","article-title":"BiLMa: Bidirectional local-matching for text-based person re-identification","author":"Fujii","year":"2023"},{"key":"10.1016\/j.patcog.2026.114324_b33","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."},{"key":"10.1016\/j.patcog.2026.114324_b34","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22010","article-title":"UFineBench: Towards text-based person retrieval with ultra-fine granularity","author":"Zuo","year":"2024"},{"key":"10.1016\/j.patcog.2026.114324_b35","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"465","article-title":"An empirical study of clip for text-based person search","volume":"Vol. 38","author":"Cao","year":"2024"},{"issue":"3","key":"10.1016\/j.patcog.2026.114324_b36","doi-asserted-by":"crossref","first-page":"5097","DOI":"10.1109\/TNNLS.2024.3368217","article-title":"Improving text-based person retrieval by excavating all-round information beyond color","volume":"36","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114324_b37","first-page":"1","article-title":"SPCL: Semantic polymorphism and commonality learning for text-based person retrieval","author":"Li","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"12","key":"10.1016\/j.patcog.2026.114324_b38","doi-asserted-by":"crossref","first-page":"17973","DOI":"10.1109\/TNNLS.2023.3310118","article-title":"Image-specific information suppression and implicit local alignment for text-based person search","volume":"35","author":"Yan","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114324_b39","series-title":"Adam: A method for Stochastic optimization","author":"Kingma","year":"2015"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012896?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012896?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T07:35:16Z","timestamp":1782718516000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012896"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":39,"alternative-id":["S0031320326012896"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114324","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Auto-Feedback Semantic Interface Learning for Text-Based Person Retrieval","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114324","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114324"}}