{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:40Z","timestamp":1777865380018,"version":"3.51.4"},"reference-count":63,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01875","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20157-20167","source":"Crossref","is-referenced-by-count":0,"title":["ProbMED: A Probabilistic Framework for Medical Multimodal Binding"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Gao","sequence":"first","affiliation":[{"name":"Peter Munk Cardiac Centre"}]},{"given":"Sangwook","family":"Kim","sequence":"additional","affiliation":[{"name":"Peter Munk Cardiac Centre"}]},{"given":"Jianzhong","family":"You","sequence":"additional","affiliation":[{"name":"Peter Munk Cardiac Centre"}]},{"given":"Chris","family":"McIntosh","sequence":"additional","affiliation":[{"name":"Peter Munk Cardiac Centre"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehad782"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103298"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2013.2290491"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref6","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010287"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02959-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-017-1625-y"},{"key":"ref10","article-title":"Improved probabilistic image-text representations","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chun","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref14","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejheart.2004.09.004"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_21"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref18","article-title":"Mimic-iv-echo: Echocardiogram matched subset (version 0.1)","author":"Gow","year":"2023","journal-title":"PhysioNet"},{"key":"ref19","author":"Gow","year":"2023","journal-title":"Mimic-iv-ecg-diagnostic electrocardiogram matched subset"},{"key":"ref20","article-title":"Developing generalist foundation models from a multimodal dataset for 3d computed tomography","author":"Ethem Hamamci","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref23","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"International conference on machine learning","author":"Ioffe","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2013.2284099"},{"key":"ref26","article-title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","author":"Johnson","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref29","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref30","first-page":"1708517104","article-title":"Probabilistic contrastive learning recovers the correct aleatoric uncertainty of ambiguous inputs","volume-title":"International Conference on Machine Learning","author":"Kirchhof","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3294980"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1166\/jmihi.2018.2442"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref36","article-title":"The music database: Sudden cardiac death in heart failure patients","author":"Mart\u0131n-Yebra","year":"2024","journal-title":"Computing in Cardiology"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooaf122"},{"key":"ref38","article-title":"Accessed: 2025-03-05","volume-title":"Swin-tiny patch4 window7 224","author":"Face","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref40","article-title":"Modeling uncertainty with hedged instance embeddings","volume-title":"International Conference on Learning Representations","author":"Joon Oh","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref42","article-title":"Echonet-dynamic: a large new cardiac motion video data resource for medical machine learning","volume-title":"NeurIPS MLAH Workshop: Vancouver, BC, Canada","author":"Ouyang","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s00392-021-01836-9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1201\/9781420034813"},{"key":"ref45","article-title":"Multimodal generative ai for precision health","author":"Poon","year":"2023","journal-title":"NEJM AI Sponsored"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref47","article-title":"Capabilities of gemini models in medicine","author":"Saab","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3022989"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2300138"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00182"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcmg.2017.08.007"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JTEHM.2022.3167009"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-0495-6"},{"key":"ref56","article-title":"Medclip: Contrastive learning from unpaired medical images and text. In Proceedings of the Conference on Empirical Methods in Natural Language Processing","volume-title":"Conference on Empirical Methods in Natural Language Processing, page 3876","author":"Wang","year":"2022"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01954"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08378-w"},{"key":"ref59","first-page":"2024","article-title":"Genomics-fm: Universal foundation model for versatile and data-efficient functional genomic analysis","author":"Ye","year":"2024","journal-title":"bioRxiv"},{"key":"ref60","article-title":"X2ct-clip: Enable multi-abnormality detection in computed tomography from chest radiography via tri-modal contrastive learning","author":"You","year":"2025","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43895-0_10"},{"key":"ref62","article-title":"Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Machine learning for healthcare conference","author":"Zhang","year":"2022"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444411.pdf?arnumber=11444411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:01Z","timestamp":1777530181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444411\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01875","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}