{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T22:39:30Z","timestamp":1793745570521,"version":"4.6.1"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,28]],"date-time":"2026-11-28T00:00:00Z","timestamp":1795824000000},"content-version":"am","delay-in-days":241,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM160515"],"award-info":[{"award-number":["R01GM160515"]}],"id":[{"id":"10.13039\/100000002","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":[[2026,4]]},"DOI":"10.1016\/j.patcog.2025.112742","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T17:29:53Z","timestamp":1763659793000},"page":"112742","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"PD","title":["A variational Bayesian approach for multimodal multi-instance classification"],"prefix":"10.1016","volume":"172","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2746-4935","authenticated-orcid":false,"given":"Yaofang","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9881-0762","authenticated-orcid":false,"given":"Yichen","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2360-5574","authenticated-orcid":false,"given":"Yusen","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8561-6511","authenticated-orcid":false,"given":"Xinlei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1\u20132","key":"10.1016\/j.patcog.2025.112742_bib0001","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","article-title":"Solving the multiple instance problem with axis-parallel rectangles","volume":"89","author":"Dietterich","year":"1997","journal-title":"Artif. Intell."},{"key":"10.1016\/j.patcog.2025.112742_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2022.102673","article-title":"Deep semi-supervised multiple instance learning with self-correction for DME classification from OCT images","volume":"83","author":"Wang","year":"2023","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.patcog.2025.112742_bib0003","article-title":"Variational multiple-Instance learning with embedding correlation modeling for hyperspectral target detection","author":"Yang","year":"2024","journal-title":"IEEE Trans. Neural. Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2025.112742_bib0004","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3669","article-title":"Phrase-level temporal relationship mining for temporal sentence localization","volume":"37","author":"Zheng","year":"2023"},{"issue":"1","key":"10.1016\/j.patcog.2025.112742_bib0005","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1214\/23-AOAS1780","article-title":"Bayesian multiple instance classification based on hierarchical probit regression","volume":"18","author":"Xiong","year":"2024","journal-title":"Ann. Appl. Stat."},{"key":"10.1016\/j.patcog.2025.112742_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.csda.2024.107954","article-title":"Variable selection in bayesian multiple instance regression using shotgun stochastic search","volume":"196","author":"Park","year":"2024","journal-title":"Comput. Stat. Data Anal."},{"key":"10.1016\/j.patcog.2025.112742_bib0007","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.neucom.2020.03.077","article-title":"Multiple-instance ranking based deep hashing for multi-label image retrieval","volume":"402","author":"Chen","year":"2020","journal-title":"Neurocomputing"},{"issue":"5","key":"10.1016\/j.patcog.2025.112742_bib0008","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1109\/TNN.2011.2109011","article-title":"Maximum margin multiple instance clustering with applications to image and text clustering","volume":"22","author":"Zhang","year":"2011","journal-title":"IEEE Trans. Neural Networks"},{"issue":"1","key":"10.1016\/j.patcog.2025.112742_bib0009","first-page":"446","article-title":"Milr: multiple-instance logistic regression with lasso penalty","volume":"9","author":"Chen","year":"2017","journal-title":"R Journal"},{"key":"10.1016\/j.patcog.2025.112742_bib0010","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.ijhm.2017.12.008","article-title":"Effects of user-provided photos on hotel review helpfulness: an analytical approach with deep leaning","volume":"71","author":"Ma","year":"2018","journal-title":"Int. J. Hosp. Manag."},{"key":"10.1016\/j.patcog.2025.112742_bib0011","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"17449","article-title":"Enhance vision-language alignment with noise","volume":"39","author":"Huang","year":"2025"},{"key":"10.1016\/j.patcog.2025.112742_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14433","article-title":"Discriminative multi-modality speech recognition","author":"Xu","year":"2020"},{"issue":"6","key":"10.1016\/j.patcog.2025.112742_bib0013","doi-asserted-by":"crossref","first-page":"2125","DOI":"10.1109\/JBHI.2020.3038889","article-title":"Deep multi-instance learning using multi-modal data for diagnosis of lymphocytosis","volume":"25","author":"Sahasrabudhe","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.patcog.2025.112742_bib0014","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"529","article-title":"Multi-modal multi-instance learning using weakly correlated histopathological images and tabular clinical information","author":"Li","year":"2021"},{"key":"10.1016\/j.patcog.2025.112742_bib0015","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.artint.2013.06.003","article-title":"Multiple instance classification: review, taxonomy and comparative study","volume":"201","author":"Amores","year":"2013","journal-title":"Artif. Intell."},{"key":"10.1016\/j.patcog.2025.112742_bib0016","article-title":"Em-dd: an improved multiple-instance learning technique","volume":"14","author":"Zhang","year":"2001","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2025.112742_bib0017","article-title":"Support vector machines for multiple-instance learning","volume":"15","author":"Andrews","year":"2002","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2025.112742_bib0018","series-title":"Proceedings of the 22Nd International Conference on Machine Learning","first-page":"697","article-title":"Supervised versus multiple instance learning: an empirical comparison","author":"Ray","year":"2005"},{"key":"10.1016\/j.patcog.2025.112742_bib0019","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/j.patcog.2017.10.009","article-title":"Multiple instance learning: a survey of problem characteristics and applications","volume":"77","author":"Carbonneau","year":"2018","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2025.112742_bib0020","series-title":"Workshop on Faces in \u2018Real-Life\u2019 Images: Detection, Alignment, and Recognition","article-title":"Simultaneous learning and alignment: multi-instance and multi-pose learning","author":"Babenko","year":"2008"},{"key":"10.1016\/j.patcog.2025.112742_bib0021","series-title":"Proceedings of the Seventeenth International Conference on Machine Learning","first-page":"1119","article-title":"Solving the multiple-Instance problem: a lazy learning approach","author":"Wang","year":"2000"},{"key":"10.1016\/j.patcog.2025.112742_bib0022","series-title":"Proceedings of the 19Th International Conference on Machine Learning","first-page":"179","article-title":"Multi-instance kernels","author":"G\u00e4rtner","year":"2002"},{"key":"10.1016\/j.patcog.2025.112742_bib0023","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s11263-006-9794-4","article-title":"Local features and kernels for classification of texture and object categories: a comprehensive study","volume":"73","author":"Zhang","year":"2007","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patcog.2025.112742_bib0024","series-title":"Proceedings of the 26Th Annual International Conference on Machine Learning","first-page":"1249","article-title":"Multi-instance learning by treating instances as non-iid samples","author":"Zhou","year":"2009"},{"issue":"1","key":"10.1016\/j.patcog.2025.112742_bib0025","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1016\/j.patcog.2014.07.022","article-title":"Multiple instance learning with bag dissimilarities","volume":"48","author":"Cheplygina","year":"2015","journal-title":"Pattern Recognit."},{"issue":"12","key":"10.1016\/j.patcog.2025.112742_bib0026","doi-asserted-by":"crossref","first-page":"1931","DOI":"10.1109\/TPAMI.2006.248","article-title":"Miles: multiple-instance learning via embedded instance selection","volume":"28","author":"Chen","year":"2006","journal-title":"IEEE Trans. Pattern. Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2025.112742_bib0027","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/s10115-006-0029-3","article-title":"Solving multi-instance problems with classifier ensemble based on constructive clustering","volume":"11","author":"Zhou","year":"2007","journal-title":"Knowl. Inf. Syst."},{"key":"10.1016\/j.patcog.2025.112742_bib0028","doi-asserted-by":"crossref","first-page":"3255","DOI":"10.1016\/j.csbj.2021.05.038","article-title":"A comparative study of multiple instance learning methods for cancer detection using T-cell receptor sequences","volume":"19","author":"Xiong","year":"2021","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"10.1016\/j.patcog.2025.112742_bib0029","series-title":"Proceedings of the 18Th International Conference on Machine Learning","first-page":"425","article-title":"Multiple instance regression","author":"Ray","year":"2001"},{"key":"10.1016\/j.patcog.2025.112742_bib0030","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part VIII 24","first-page":"45","article-title":"Mil-vt: multiple instance learning enhanced vision transformer for fundus image classification","author":"Yu","year":"2021"},{"key":"10.1016\/j.patcog.2025.112742_bib0031","series-title":"Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part VIII 24","first-page":"55","article-title":"Local-global dual perception based deep multiple instance learning for retinal disease classification","author":"Bi","year":"2021"},{"key":"10.1016\/j.patcog.2025.112742_bib0032","doi-asserted-by":"crossref","first-page":"4911","DOI":"10.1109\/TIP.2020.2975718","article-title":"A multiple-instance densely-connected convnet for aerial scene classification","volume":"29","author":"Bi","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.patcog.2025.112742_bib0033","series-title":"Proceedings of the 29Th ACM International Conference on Multimedia","first-page":"2474","article-title":"Multi-modal multi-instance learning for retinal disease recognition","author":"Li","year":"2021"},{"issue":"422","key":"10.1016\/j.patcog.2025.112742_bib0034","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1080\/01621459.1993.10476321","article-title":"Bayesian analysis of binary and polychotomous response data","volume":"88","author":"Albert","year":"1993","journal-title":"J. Am. Stat. Assoc."},{"issue":"518","key":"10.1016\/j.patcog.2025.112742_bib0035","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","article-title":"Variational inference: a review for statisticians","volume":"112","author":"Blei","year":"2017","journal-title":"J. Am. Stat. Assoc."},{"key":"10.1016\/j.patcog.2025.112742_bib0036","article-title":"Variational positive-incentive noise: how noise benefits models","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2025.112742_bib0037","series-title":"Pattern Recognition and Machine Learning","author":"Bishop","year":"2006"},{"key":"10.1016\/j.patcog.2025.112742_bib0038","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"305","article-title":"Vistanet: visual aspect attention network for multimodal sentiment analysis","volume":"33","author":"Truong","year":"2019"},{"key":"10.1016\/j.patcog.2025.112742_bib0039","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.2025.112742_bib0040","unstructured":"D.P. Kingma, M. Welling, Auto-encoding variational Bayes, (2013). arXiv preprint arXiv:1312.6114."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320325014050?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320325014050?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T12:59:29Z","timestamp":1773838769000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320325014050"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":40,"alternative-id":["S0031320325014050"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2025.112742","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A variational Bayesian approach for multimodal multi-instance classification","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2025.112742","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"112742"}}