{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T13:28:16Z","timestamp":1792070896230,"version":"4.4.0"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.02139","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:55:59Z","timestamp":1705352159000},"page":"23346-23356","source":"Crossref","is-referenced-by-count":33,"title":["Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts"],"prefix":"10.1109","author":[{"given":"Zhihong","family":"Chen","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shizhe","family":"Diao","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benyou","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Wan","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Vqa-med: Overview of the medical visual question answering task at imageclef 2019","author":"Abacha","year":"2019","journal-title":"CLEF"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1909"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01442"},{"key":"ref4","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","author":"Bao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"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"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547948"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref12","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"International Conference on Machine Learning","author":"Cho"},{"key":"ref13","first-page":"85","article-title":"Meteor 1.3: Automatic metric for reliable optimization and evaluation of machine translation systems","volume-title":"Proceedings of the sixth workshop on statistical machine translation","author":"Denkowski"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref15","article-title":"Prefix language models are unified modal learners","author":"Diao","year":"2022"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref21","article-title":"Pixel-bert: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref23","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"ref26","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref28","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","article-title":"Visualbert: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM49941.2020.9313289"},{"key":"ref33","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1387"},{"key":"ref38","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref39","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref40","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"Mixed precision training","volume-title":"International Conference on Learning Representations","author":"Micikevicius"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.416"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3207502"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_39"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1187"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref52","article-title":"Vl-bert: Pre-training of generic visual-linguistic representations","volume-title":"International Conference on Learning Representations","author":"Su"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.191"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref56","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","author":"Wang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref57","first-page":"23318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref60","first-page":"2023","article-title":"Medklip: Medical knowledge enhanced language-image pre-training","author":"Wu","year":"2023","journal-title":"medRxiv"},{"key":"ref61","article-title":"Google\u2019s neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"ref62","article-title":"Filip: Fine-grained interactive language-image pre-training","volume-title":"International Conference on Learning Representations","author":"Yao"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref65","article-title":"Contrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2020"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Paris, France","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10378529.pdf?arnumber=10378529","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:47:40Z","timestamp":1705542460000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10378529\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.02139","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}