{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:38:31Z","timestamp":1784183911219,"version":"3.55.0"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003452","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003452","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00162","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1610-1620","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal Medical Image Binding via Shared Text Embeddings"],"prefix":"10.1109","author":[{"given":"Yunhao","family":"Liu","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suyang","family":"Xi","sequence":"additional","affiliation":[{"name":"Emory University,Atlanta,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong Lingnan University,Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago,Chicago,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chicheng","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chong","family":"Zhong","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjun","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catherine C.","family":"Liu","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University,Department of Data Science and Artificial Intelligence,Hong Kong,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqing","family":"Shen","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehv318"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w19-1909"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-012-2247-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s13244-012-0196-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5566\/ias.1155"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101857"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_21"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2014.04.013"},{"key":"ref12","first-page":"13","article-title":"Mimic-iv-ecg: Diagnostic electrocardiogram matched subset","volume":"6","author":"Gow","year":"2023","journal-title":"Type: dataset"},{"key":"ref13","article-title":"A foundation model utilizing chest ct volumes and radiology reports for supervised-level zero-shot detection of abnormalities","author":"Hamamci","year":"2024"},{"key":"ref14","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref15","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02504-3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/5164970"},{"key":"ref19","author":"Ikezogwo","year":"2023","journal-title":"Quilt-1m: One million image-text pairs for histopathology"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref22","article-title":"Unimed-clip: Towards a unified image-text pretraining paradigm for diverse medical imaging modalities","author":"Khattak","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.1022967"},{"key":"ref24","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on machine learning","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCIMAGING.108.784876"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1166\/jmihi.2018.2442"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195140903.001.0001"},{"key":"ref30","first-page":"82","article-title":"Electrocardiography","volume":"1","author":"Mirvis","year":"2001","journal-title":"Heart disease"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref32","first-page":"529","article-title":"Slip: Self-supervision meets language-image pretraining","volume-title":"European Conference on computer vision","author":"Mu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/nrclinonc.2016.162"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.14141356"},{"key":"ref36","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105637"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103357"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00025"},{"issue":"529","key":"ref40","first-page":"574","article-title":"Chest radiography in general practice: indications, diagnostic yield and consequences for patient management","volume":"56","author":"Speets","year":"2006","journal-title":"British Journal of General Practice"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01423"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"ref43","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_24"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-020-0495-6"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2430"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25359"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02008"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01510"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35505"},{"key":"ref52","article-title":"Filip: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2400640"},{"key":"ref54","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"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803074"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103551"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492076.pdf?arnumber=11492076","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:54:02Z","timestamp":1778046842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492076\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00162","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}