{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:03:48Z","timestamp":1784531028265,"version":"3.55.0"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"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":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.imavis.2026.106069","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:19:35Z","timestamp":1782404375000},"page":"106069","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Dual uncertainty-aware hierarchical semantic matching for text-to-image person search"],"prefix":"10.1016","volume":"173","author":[{"given":"Ting","family":"Tuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"11","key":"10.1016\/j.imavis.2026.106069_bb0005","doi-asserted-by":"crossref","first-page":"126","DOI":"10.3390\/jimaging6110126","article-title":"A Siamese neural network for non-invasive baggage re-identification","volume":"6","author":"Mazzeo","year":"2020","journal-title":"J. Imaging"},{"key":"10.1016\/j.imavis.2026.106069_bb0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105400","article-title":"Robust auxiliary modality is beneficial for video-based cloth-changing person re-identification","volume":"154","author":"Chen","year":"2025","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106069_bb0015","article-title":"Person search with natural language description","author":"Li","year":"2017","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0020","article-title":"Pose-guided multi-granularity attention network for text-based person search","author":"Jing","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0025","series-title":"Dynamic position-aware network for fine-grained image recognition","first-page":"2791","author":"Wang","year":"2021"},{"key":"10.1016\/j.imavis.2026.106069_bb0030","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.imavis.2026.106069_bb0035","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0040","article-title":"CLIP-driven fine-grained text-image person re-identification","author":"IEEE Xplore","year":"2025","journal-title":"IEEE Journals & Magazine"},{"key":"10.1016\/j.imavis.2026.106069_bb0050","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.imavis.2026.106069_bb0055","series-title":"Unified Pre-Training with Pseudo Texts for Text-To-Image Person Re-Identification","first-page":"11174","article-title":"presented at the Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Shao","year":"2023"},{"key":"10.1016\/j.imavis.2026.106069_bb0060","series-title":"Embracing Unimodal Aleatoric Uncertainty for Robust Multimodal Fusion","first-page":"26876","article-title":"presented at the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Gao","year":"2024"},{"key":"10.1016\/j.imavis.2026.106069_bb0065","article-title":"Why machine learning models fail to fully capture epistemic uncertainty","author":"Jim\u00e9nez","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0070","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.imavis.2026.106069_bb0085","doi-asserted-by":"crossref","first-page":"2350","DOI":"10.1109\/LSP.2024.3456007","article-title":"Text-guided prototype generation for occluded person re-identification","volume":"31","author":"Jiang","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.imavis.2026.106069_bb0090","doi-asserted-by":"crossref","first-page":"6025","DOI":"10.1109\/TMM.2023.3344354","article-title":"Text-to-image person re-identification based on multimodal graph convolutional network","volume":"26","author":"Han","year":"2024","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.imavis.2026.106069_bb0095","series-title":"Deep Gaussian Processes: a Survey","author":"Jakkala","year":"2021"},{"issue":"5","key":"10.1016\/j.imavis.2026.106069_bb0105","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1007\/s11227-025-07158-1","article-title":"Noise correspondence with evidence learning for text-based person search","volume":"81","author":"Xie","year":"2025","journal-title":"J. Supercomput."},{"key":"10.1016\/j.imavis.2026.106069_bb0110","series-title":"Fast R-CNN","first-page":"1440","author":"Girshick","year":"2015"},{"key":"10.1016\/j.imavis.2026.106069_bb0120","series-title":"Advances in Neural Information Processing Systems","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021"},{"key":"10.1016\/j.imavis.2026.106069_bb0125","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 Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106069_bb0130","article-title":"Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval","author":"Jiang","year":"2023","journal-title":"arXiv"},{"issue":"10","key":"10.1016\/j.imavis.2026.106069_bb0135","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":"Int. J. Comput. Vis."},{"key":"10.1016\/j.imavis.2026.106069_bb0140","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"474","article-title":"PLOT: Text-based person search with part slot attention for corresponding part discovery","author":"Park","year":"2025"},{"key":"10.1016\/j.imavis.2026.106069_bb0145","series-title":"Proceedings of the ACM on Web Conference 2025","first-page":"2341","author":"Sun","year":"2025"},{"issue":"12","key":"10.1016\/j.imavis.2026.106069_bb0150","first-page":"14052","article-title":"Causality-inspired invariant representation learning for text-based person retrieval","volume":"38","author":"Liu","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.imavis.2026.106069_bb0160","series-title":"presented at the Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8415","article-title":"Probabilistic Embeddings for Cross-Modal Retrieval","author":"Chun","year":"2021"},{"key":"10.1016\/j.imavis.2026.106069_bb0165","article-title":"Improved probabilistic image-text representations","author":"Chun","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0170","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2830","author":"Wang","year":"2023"},{"key":"10.1016\/j.imavis.2026.106069_bb0180","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"390","article-title":"Uncertainty-aware sign language video retrieval with probability distribution modeling","author":"Wu","year":"2025"},{"key":"10.1016\/j.imavis.2026.106069_bb0185","article-title":"Probabilistic language-image pre-training","author":"Chun","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0190","article-title":"GROVE: a retrieval-augmented complex story generation framework with a forest of evidence","author":"Wen","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0195","article-title":"BayesAdapter: enhanced uncertainty estimation in CLIP few-shot adaptation","author":"Morales-\u00c1lvarez","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0200","series-title":"Proceedings of the 31st ACM International Conference on Multimedia, in MM \u201823","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.imavis.2026.106069_bb0205","article-title":"Prototypical prompting for text-to-image person re-identification","author":"Yan","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0215","series-title":"Advances in Neural Information Processing Systems","first-page":"5875","article-title":"Stochastic Deep Gaussian Processes over Graphs","author":"Li","year":"2020"},{"key":"10.1016\/j.imavis.2026.106069_bb0220","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0225","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0230","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"Kendall","year":"2018","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0235","article-title":"MAP: multimodal uncertainty-aware vision-language pre-training model","author":"Ji","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0240","article-title":"DSSL: deep surroundings-person separation learning for text-based person retrieval","author":"Zhu","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0245","article-title":"Noisy-correspondence learning for text-to-image person re-identification","author":"Qin","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0250","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 Trans. Image Process."},{"key":"10.1016\/j.imavis.2026.106069_bb0255","series-title":"presented at the 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.imavis.2026.106069_bb0260","series-title":"ViTAA: visual-textual attributes alignment in person search by natural language","year":"2025"},{"key":"10.1016\/j.imavis.2026.106069_bb0265","unstructured":"Z. Ding, C. Ding, Z. Shao, and D. Tao, \u201cSemantically self-aligned network for text-to-image part-aware person re-identification,\u201d 2021, arXiv: arXiv:2107.12666. doi:10.48550\/arXiv.2107.12666."},{"key":"10.1016\/j.imavis.2026.106069_bb0270","doi-asserted-by":"crossref","first-page":"7699","DOI":"10.1109\/TMM.2022.3225754","article-title":"Asymmetric cross-scale alignment for text-based person search","volume":"25","author":"Ji","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.imavis.2026.106069_bb0275","series-title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","first-page":"555","article-title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","author":"Bai","year":"2023"},{"key":"10.1016\/j.imavis.2026.106069_bb0285","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103644","article-title":"Dual alignment: partial negative and soft-label alignment for text-to-image person retrieval","volume":"127","author":"Song","year":"2026","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106069_bb0295","series-title":"Proceedings of the 31st ACM International Conference on Multimedia, in MM \u201823","first-page":"4492","article-title":"Towards unified text-based person retrieval: A large-scale multi-attribute and language search benchmark","author":"Yang","year":"2023"},{"key":"10.1016\/j.imavis.2026.106069_bb0300","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114014","article-title":"Towards unified bijective image\u2013text generation for text-to-image person re-identification","volume":"325","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.imavis.2026.106069_bb0305","article-title":"Knowing where to focus: attention-guided alignment for text-based person search","author":"Tan","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0310","series-title":"ICASSP 2025\u20132025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Prototypical Graph Alignment for Text-based Person Search","author":"Huang","year":"2025"},{"issue":"24","key":"10.1016\/j.imavis.2026.106069_bb0315","doi-asserted-by":"crossref","first-page":"55046","DOI":"10.1109\/JIOT.2025.3621864","article-title":"Cross-modal alignment enhancement network for text-to-image person re-identification","volume":"12","author":"He","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.imavis.2026.106069_bb0320","article-title":"VGSG: vision-guided semantic-group network for text-based person search","author":"He","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0325","article-title":"UP-Person: unified parameter-efficient transfer learning for text-based person retrieval","author":"Liu","year":"2025","journal-title":"arXiv"},{"key":"10.1016\/j.imavis.2026.106069_bb0330","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.113293","article-title":"Dual-level information interactive learning model for text-image person re-identification","volume":"164","author":"Sun","year":"2026","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.imavis.2026.106069_bb0335","series-title":"A computer-assisted medical diagnosis system for cancer diseases based on quaternion orthogonal Rademacher-Fourier moments and deep learning","year":"2026"},{"key":"10.1016\/j.imavis.2026.106069_bb0340","series-title":"3D image recognition using new set of fractional-order Legendre moments and deep neural networks","year":"2026"}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001769?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001769?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T06:23:41Z","timestamp":1784528621000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626001769"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":58,"alternative-id":["S0262885626001769"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106069","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Dual uncertainty-aware hierarchical semantic matching for text-to-image person search","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106069","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106069"}}