{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T11:01:40Z","timestamp":1780484500334,"version":"3.54.1"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1016\/j.patcog.2023.109636","type":"journal-article","created":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T01:57:23Z","timestamp":1682301443000},"page":"109636","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":31,"special_numbering":"C","title":["BDNet: A BERT-based dual-path network for text-to-image cross-modal person re-identification"],"prefix":"10.1016","volume":"141","author":[{"given":"Qiang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohai","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qizhi","family":"Teng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linbo","family":"Qing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0502-8796","authenticated-orcid":false,"given":"Honggang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2023.109636_bib0001","doi-asserted-by":"crossref","first-page":"107424","DOI":"10.1016\/j.patcog.2020.107424","article-title":"Deep features for person re-identification on metric learning","volume":"110","author":"Wu","year":"2021","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2023.109636_bib0002","doi-asserted-by":"crossref","first-page":"108567","DOI":"10.1016\/j.patcog.2022.108567","article-title":"Deep attention aware feature learning for person re-identification","volume":"126","author":"Chen","year":"2022","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2023.109636_bib0003","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","volume":"29","author":"Niu","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2023.109636_bib0004","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1970","article-title":"Person search with natural language description","author":"Li","year":"2017"},{"key":"10.1016\/j.patcog.2023.109636_bib0005","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.patcog.2023.109636_bib0006","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"2057","article-title":"Language person search with mutually connected classification loss","author":"Wang","year":"2019"},{"key":"10.1016\/j.patcog.2023.109636_bib0007","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1724","article-title":"Learning phrase representations using RNN encoderdecoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"10.1016\/j.patcog.2023.109636_sbref0008","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"10.1016\/j.patcog.2023.109636_bib0009","doi-asserted-by":"crossref","first-page":"104168","DOI":"10.1016\/j.imavis.2021.104168","article-title":"Dual-path CNN with max gated block for text-based person re-identification","volume":"111","author":"Ma","year":"2021","journal-title":"Image Vis Comput"},{"key":"10.1016\/j.patcog.2023.109636_bib0010","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11189","article-title":"Pose-guided multi-granularity attention network for text-based person search","volume":"volume\u00a034","author":"Jing","year":"2020"},{"key":"10.1016\/j.patcog.2023.109636_sbref0011","article-title":"TIPCB: a simple but effective part-based convolutional baseline for text-based person search","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv:2105.11628"},{"key":"10.1016\/j.patcog.2023.109636_bib0012","series-title":"Advances in Neural Information Processing Systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.patcog.2023.109636_sbref0013","article-title":"In defense of the triplet loss for person re-identification","author":"Hermans","year":"2017","journal-title":"arXiv preprint arXiv:1703.07737"},{"key":"10.1016\/j.patcog.2023.109636_bib0014","article-title":"Deep learning for person re-identification: a survey and outlook","author":"Ye","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.patcog.2023.109636_bib0015","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"686","article-title":"Deep cross-modal projection learning for image-text matching","author":"Zhang","year":"2018"},{"key":"10.1016\/j.patcog.2023.109636_bib0016","doi-asserted-by":"crossref","first-page":"107014","DOI":"10.1016\/j.patcog.2019.107014","article-title":"Similarity learning with joint transfer constraints for person re-identification","volume":"97","author":"Zhao","year":"2020","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2023.109636_bib0017","doi-asserted-by":"crossref","first-page":"108155","DOI":"10.1016\/j.patcog.2021.108155","article-title":"Part-guided graph convolution networks for person re-identification","volume":"120","author":"Zhang","year":"2021","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2023.109636_bib0018","doi-asserted-by":"crossref","first-page":"107937","DOI":"10.1016\/j.patcog.2021.107937","article-title":"MEMF: multi-level-attention embedding and multi-layer-feature fusion model for person re-identification","volume":"116","author":"Sun","year":"2021","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2023.109636_bib0019","doi-asserted-by":"crossref","first-page":"108654","DOI":"10.1016\/j.patcog.2022.108654","article-title":"Making person search enjoy the merits of person re-identification","volume":"127","author":"Liu","year":"2022","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2023.109636_bib0020","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1116","article-title":"Scalable person re-identification: a benchmark","author":"Zheng","year":"2015"},{"key":"10.1016\/j.patcog.2023.109636_bib0021","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"3754","article-title":"Unlabeled samples generated by GAN improve the person re-identification baseline in vitro","author":"Zheng","year":"2017"},{"key":"10.1016\/j.patcog.2023.109636_bib0022","series-title":"International Conference on Pattern Recognition and Machine Intelligence","first-page":"543","article-title":"A study on deep convolutional neural network based approaches for person re-identification","author":"Chahar","year":"2017"},{"key":"10.1016\/j.patcog.2023.109636_bib0023","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/j.neucom.2019.01.079","article-title":"Deep learning-based methods for person re-identification: a comprehensive review","volume":"337","author":"Wu","year":"2019","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2023.109636_bib0024","doi-asserted-by":"crossref","first-page":"108653","DOI":"10.1016\/j.patcog.2022.108653","article-title":"Cross-modality person re-identification via multi-task learning","volume":"128","author":"Huang","year":"2022","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2023.109636_bib0025","doi-asserted-by":"crossref","first-page":"108042","DOI":"10.1016\/j.knosys.2021.108042","article-title":"Feature separation and double causal comparison loss for visible and infrared person re-identification","volume":"239","author":"Liu","year":"2022","journal-title":"Knowl Based Syst"},{"key":"10.1016\/j.patcog.2023.109636_bib0026","doi-asserted-by":"crossref","first-page":"107351","DOI":"10.1016\/j.patcog.2020.107351","article-title":"Re-ranking image-text matching by adaptive metric fusion","volume":"104","author":"Niu","year":"2020","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2023.109636_bib0027","series-title":"Proceedings of the 26th ACM international conference on Multimedia","first-page":"609","article-title":"Cross-domain adversarial feature learning for sketch re-identification","author":"Pang","year":"2018"},{"key":"10.1016\/j.patcog.2023.109636_bib0028","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"5380","article-title":"Rgb-infrared cross-modality person re-identification","author":"Wu","year":"2017"},{"key":"10.1016\/j.patcog.2023.109636_bib0029","doi-asserted-by":"crossref","first-page":"107533","DOI":"10.1016\/j.patcog.2020.107533","article-title":"Modality adversarial neural network for visible-thermal person re-identification","volume":"107","author":"Hao","year":"2020","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2023.109636_bib0030","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"5814","article-title":"Adversarial representation learning for text-to-image matching","author":"Sarafianos","year":"2019"},{"issue":"2","key":"10.1016\/j.patcog.2023.109636_bib0031","first-page":"1","article-title":"Dual-path convolutional image-text embeddings with instance loss","volume":"16","author":"Zheng","year":"2017","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"10.1016\/j.patcog.2023.109636_bib0032","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1890","article-title":"Identity-aware textual-visual matching with latent co-attention","author":"Li","year":"2017"},{"key":"10.1016\/j.patcog.2023.109636_bib0033","series-title":"2018\u00a0IEEE Winter Conference on Applications of Computer Vision (WACV)","first-page":"1879","article-title":"Improving text-based person search by spatial matching and adaptive threshold","author":"Chen","year":"2018"},{"key":"10.1016\/j.patcog.2023.109636_bib0034","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"54","article-title":"Improving deep visual representation for person re-identification by global and local image-language association","author":"Chen","year":"2018"},{"key":"10.1016\/j.patcog.2023.109636_bib0035","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"201","article-title":"Stacked cross attention for image-text matching","author":"Lee","year":"2018"},{"key":"10.1016\/j.patcog.2023.109636_bib0036","series-title":"European Conference on Computer Vision","first-page":"402","article-title":"Vitaa: Visual-textual attributes alignment in person search by natural language","author":"Wang","year":"2020"},{"key":"10.1016\/j.patcog.2023.109636_bib0037","series-title":"Proceedings of the 28th ACM International Conference on Multimedia","first-page":"3441","article-title":"Hierarchical gumbel attention network for text-based person search","author":"Zheng","year":"2020"},{"key":"10.1016\/j.patcog.2023.109636_bib0038","unstructured":"Z. Ding, C. Ding, Z. Shao, D. Tao, Semantically self-aligned network for text-to-image part-aware person re-identification, 2021, https:\/\/arxiv.org\/abs\/2107.12666."},{"key":"10.1016\/j.patcog.2023.109636_bib0039","series-title":"Proceedings of the 2021 International Conference on Multimedia Retrieval","first-page":"118","article-title":"Text-guided visual feature refinement for text-based person search","author":"Gao","year":"2021"},{"key":"10.1016\/j.patcog.2023.109636_bib0040","series-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","article-title":"Text-based person search via multi-granularity embedding learning","author":"Wang","year":"2021"},{"key":"10.1016\/j.patcog.2023.109636_sbref0040","article-title":"Text-based person search with limited data","author":"Han","year":"2021","journal-title":"arXiv preprint arXiv:2110.10807"},{"issue":"12","key":"10.1016\/j.patcog.2023.109636_bib0042","doi-asserted-by":"crossref","first-page":"1551","DOI":"10.1631\/FITEE.2100463","article-title":"Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies","volume":"22","author":"Yang","year":"2021","journal-title":"Frontiers of Information Technology and Electronic Engineering"},{"key":"10.1016\/j.patcog.2023.109636_bib0043","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"3","article-title":"CBAM: convolutional block attention module","author":"Woo","year":"2018"},{"key":"10.1016\/j.patcog.2023.109636_bib0044","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"212","article-title":"Sphereface: Deep hypersphere embedding for face recognition","author":"Liu","year":"2017"},{"key":"10.1016\/j.patcog.2023.109636_bib0045","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"13001","article-title":"Random erasing data augmentation","volume":"volume\u00a034","author":"Zhong","year":"2020"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320323003370?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320323003370?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T17:10:32Z","timestamp":1758474632000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320323003370"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":45,"alternative-id":["S0031320323003370"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2023.109636","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2023,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"BDNet: A BERT-based dual-path network for text-to-image cross-modal person re-identification","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2023.109636","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"109636"}}