{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:49:22Z","timestamp":1785908962278,"version":"3.56.0"},"reference-count":44,"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\/100007224","name":"National Foundation for Science and Technology Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007224","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007225","name":"Socialist Republic of Vietnam Ministry of Science and Technology","doi-asserted-by":"publisher","award":["NCUD.02-2025.04"],"award-info":[{"award-number":["NCUD.02-2025.04"]}],"id":[{"id":"10.13039\/100007225","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.neunet.2026.109275","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:24:43Z","timestamp":1781886283000},"page":"109275","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DNA: Improving text-based person search through distillation learning, negated relation-aware learning, and augmented representation learning"],"prefix":"10.1016","volume":"204","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5097-2401","authenticated-orcid":false,"given":"Anh D.","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9135-9779","authenticated-orcid":false,"given":"Tam T.","family":"Ngo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2565-281X","authenticated-orcid":false,"given":"Hoa N.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109275_bib0001","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.474","article-title":"Knowledge distillation in deep learning and its applications","volume":"7","author":"Alkhulaifi","year":"2021","journal-title":"PeerJ Computer Science"},{"key":"10.1016\/j.neunet.2026.109275_bib0002","series-title":"Proceedings of the thirty-second international joint conference on artificial intelligence","article-title":"RaSa: Relation and sensitivity aware representation learning for text-based person search","author":"Bai","year":"2023"},{"issue":"1","key":"10.1016\/j.neunet.2026.109275_bib0003","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1609\/aaai.v38i1.27801","article-title":"An empirical study of CLIP for text-based person search","volume":"38","author":"Cao","year":"2024","journal-title":"Proceedings of the AAAI conference on artificial intelligence"},{"key":"10.1016\/j.neunet.2026.109275_bib0004","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.neunet.2026.109275_bib0005","series-title":"Proceedings of the 2019 conference of the north American chapter of the association for computational linguistics: Human language technologies","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.neunet.2026.109275_bib0006","unstructured":"Ding, Z., Ding, C., Shao, Z., & Tao, D. (2021). Semantically self-aligned network for text-to-image part-aware person re-identification. Computer Vision and Pattern Recognition,. 10.48550\/arXiv.2107.12666."},{"key":"10.1016\/j.neunet.2026.109275_bib0007","doi-asserted-by":"crossref","DOI":"10.1145\/3721482","article-title":"MARS: Paying more attention to visual attributes for text-based person search","author":"Ergasti","year":"2025","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"issue":"4","key":"10.1016\/j.neunet.2026.109275_bib0008","doi-asserted-by":"crossref","first-page":"4477","DOI":"10.1609\/aaai.v36i4.20370","article-title":"AXM-Net: Implicit cross-modal feature alignment for person re-identification","volume":"36","author":"Farooq","year":"2022","journal-title":"Proceedings of the AAAI conference on artificial intelligence"},{"key":"10.1016\/j.neunet.2026.109275_bib0009","unstructured":"Ge, Y., Chen, D., & Li, H. (2020). Mutual mean-teaching: Pseudo label refinery for unsupervised domain adaptation on person re-identification. In International conference on learning representations. 10.48550\/arXiv.2001.01526."},{"key":"10.1016\/j.neunet.2026.109275_bib0010","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.patrec.2018.10.020","article-title":"Fusion-attention network for person search with free-form natural language","volume":"116","author":"Ji","year":"2018","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.neunet.2026.109275_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"2787","article-title":"Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval","author":"Jiang","year":"2023"},{"issue":"3","key":"10.1016\/j.neunet.2026.109275_bib0012","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","article-title":"Billion-scale similarity search with GPUs","volume":"7","author":"Johnson","year":"2021","journal-title":"IEEE Transactions on Big Data"},{"key":"10.1016\/j.neunet.2026.109275_bib0013","article-title":"Transformer based language-person search with multiple region slicing","author":"Li","year":"2021","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109275_bib0014","series-title":"Proceedings of the 35th international conference on neural information processing systems","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.109275_bib0015","series-title":"ICASSP 2022 - 2022 IEEE International conference on acoustics, speech and signal processing (ICASSP)","first-page":"2724","article-title":"Learning semantic-aligned feature representation for text-based person search","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2026.109275_bib0016","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"5187","article-title":"Person search with natural language description","author":"Li","year":"2017"},{"issue":"11","key":"10.1016\/j.neunet.2026.109275_bib0017","doi-asserted-by":"crossref","first-page":"11695","DOI":"10.1109\/TCSVT.2024.3428589","article-title":"Knowledge consistency distillation for weakly supervised one step person search","volume":"34","author":"Li","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109275_bib0018","doi-asserted-by":"crossref","first-page":"5147","DOI":"10.1109\/TIP.2025.3594880","article-title":"Enhancing text-based person retrieval by combining fused representation and reciprocal learning with adaptive loss refinement","volume":"34","author":"Nguyen","year":"2025","journal-title":"IEEE Transactions on Image Processing"},{"issue":"4","key":"10.1016\/j.neunet.2026.109275_bib0019","doi-asserted-by":"crossref","DOI":"10.1117\/1.JEI.34.4.043001","article-title":"SCM-ReID: Enhancing person re-identification by supervised contrastive-metric learning and hybrid loss optimization","volume":"34","author":"Pham","year":"2025","journal-title":"Journal of Electronic Imaging"},{"key":"10.1016\/j.neunet.2026.109275_bib0020","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.neunet.2026.109275_bib0021","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.neunet.2026.109275_bib0022","doi-asserted-by":"crossref","unstructured":"Shao, Z., Zhang, X., Ding, C., Wang, J., & Wang, J. (2023). Unified pre-training with pseudo texts for text-to-image person re-identification. 10.1109\/ICCV51070.2023.01026.","DOI":"10.1109\/ICCV51070.2023.01026"},{"key":"10.1016\/j.neunet.2026.109275_bib0023","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"5566","article-title":"Learning granularity-unified representations for text-to-image person re-identification","author":"Shao","year":"2022"},{"key":"10.1016\/j.neunet.2026.109275_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112893","article-title":"Enhancing visual representation for text-based person searching","volume":"309","author":"Shen","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2026.109275_bib0025","series-title":"Proceedings of the European conference on computer vision workshops (ECCVW)","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.neunet.2026.109275_bib0026","unstructured":"Singh, J., Shrivastava, I., Vatsa, M., Singh, R., & Bharati, A. (2024). Learn \u201cno\u201d to say \u201cyes\u201d better: Improving vision-language models via negations. 10.48550\/arXiv.2403.20312."},{"issue":"10","key":"10.1016\/j.neunet.2026.109275_bib0027","doi-asserted-by":"crossref","first-page":"4440","DOI":"10.1007\/s11263-024-02094-8","article-title":"An adaptive correlation filtering method for text-based person search","volume":"132","author":"Sun","year":"2024","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109275_bib0028","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.patrec.2023.03.008","article-title":"Counterfactual attention alignment for visible-infrared cross-modality person re-identification","volume":"168","author":"Sun","year":"2023","journal-title":"Pattern Recognition Letters"},{"key":"10.1016\/j.neunet.2026.109275_bib0029","series-title":"Computer vision \u2013 ECCV 2022","first-page":"726","article-title":"A simple and robust correlation filtering method for text-based person search","author":"Suo","year":"2022"},{"key":"10.1016\/j.neunet.2026.109275_bib0030","series-title":"Proceedings of the 31st international conference on neural information processing systems","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"Tarvainen","year":"2017"},{"key":"10.1016\/j.neunet.2026.109275_bib0031","series-title":"2023 IEEE\/CVF International conference on computer vision","first-page":"1802","article-title":"Clipn for zero-shot ood detection: Teaching clip to say no","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109275_bib0032","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"1984","article-title":"Look before you leap: Improving text-based person retrieval by learning a consistent cross-modal common manifold","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109275_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.104912","article-title":"EESSO: Exploiting extreme and smooth signals via omni-frequency learning for text-based person retrieval","volume":"142","author":"Xue","year":"2024","journal-title":"Image and Vision Computing"},{"key":"10.1016\/j.neunet.2026.109275_bib0034","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"6202","article-title":"Learning comprehensive representations with richer self for text-to-image person re-identification","author":"Yan","year":"2023"},{"key":"10.1016\/j.neunet.2026.109275_bib0035","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 Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2026.109275_bib0036","series-title":"Proceedings of the ACM international conference on multimedia (ACM MM)","first-page":"4492","article-title":"Towards unified text-based person retrieval: A large-scale multi-attribute and language search benchmark","author":"Yang","year":"2023"},{"issue":"1","key":"10.1016\/j.neunet.2026.109275_bib0037","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1109\/TCSVT.2021.3058668","article-title":"Bottom-up foreground-aware feature fusion for practical person search","volume":"32","author":"Yang","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2026.109275_bib0038","article-title":"Hierarchical knowledge-guided reasoning for text-based person re-identification","volume":"in press","author":"Zeng","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109275_bib0039","series-title":"Computer vision \u2013 ECCV 2018","first-page":"707","article-title":"Deep cross-modal projection learning for image-text matching","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neunet.2026.109275_bib0040","series-title":"2017 IEEE Conference on computer vision and pattern recognition","first-page":"3652","article-title":"Re-ranking person re-identification with k-reciprocal encoding","author":"Zhong","year":"2017"},{"key":"10.1016\/j.neunet.2026.109275_bib0041","series-title":"Proceedings of the 29th ACM international conference on multimedia","first-page":"209","article-title":"DSSL: Deep surroundings-person separation learning for text-based person retrieval","author":"Zhu","year":"2021"},{"issue":"3","key":"10.1016\/j.neunet.2026.109275_bib0042","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 Transactions on Neural Networks and Learning Systems"},{"issue":"11","key":"10.1016\/j.neunet.2026.109275_bib0043","doi-asserted-by":"crossref","first-page":"2959","DOI":"10.1007\/s11263-023-01841-7","article-title":"Attribute-image person re-identification via modal-consistent metric learning","volume":"131","author":"Zhu","year":"2023","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109275_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.104921","article-title":"Feature attention fusion network for occluded person re-identification","volume":"143","author":"Zhuang","year":"2024","journal-title":"Image and Vision Computing"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026007355?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026007355?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:24:38Z","timestamp":1785907478000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026007355"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":44,"alternative-id":["S0893608026007355"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109275","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DNA: Improving text-based person search through distillation learning, negated relation-aware learning, and augmented representation learning","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109275","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":"109275"}}