{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:36:19Z","timestamp":1782394579477,"version":"3.54.5"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grants Council (RGC) General Research Fund","award":["14204321"],"award-info":[{"award-number":["14204321"]}]},{"name":"Hong Kong Research Grants Council (RGC) General Research Fund","award":["14220622"],"award-info":[{"award-number":["14220622"]}]},{"name":"Hong Kong Research Grants Council (RGC) General Research Fund","award":["11211221"],"award-info":[{"award-number":["11211221"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tmi.2024.3418408","type":"journal-article","created":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T17:25:20Z","timestamp":1719249920000},"page":"4224-4235","source":"Crossref","is-referenced-by-count":19,"title":["MCPL: Multi-Modal Collaborative Prompt Learning for Medical Vision-Language Model"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0997-9887","authenticated-orcid":false,"given":"Pengyu","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2552-9640","authenticated-orcid":false,"given":"Huaqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0853-6948","authenticated-orcid":false,"given":"Yixuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. ICLR","author":"Su"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref3","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref4","first-page":"1","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"Proc. ICLR","author":"Yao"},{"key":"ref5","first-page":"493","article-title":"Tip-adapter: Training-free CLIP-adapter for better vision-language modeling","volume-title":"Proc. ECCV","author":"Zhang"},{"key":"ref6","first-page":"1","article-title":"CLIP-adapter: Better vision-language models with feature adapters","volume":"132","author":"Gao","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref8","article-title":"BiomedCLIP: A multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023","journal-title":"arXiv:2303.00915"},{"key":"ref9","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.197"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00635"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3291588"},{"key":"ref19","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref20","article-title":"OpenFlamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023","journal-title":"arXiv:2308.01390"},{"key":"ref21","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref22","first-page":"1","article-title":"CoBIT: A contrastive bi-directional image-text generation model","volume-title":"Proc. ICLR","author":"You"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref24","first-page":"38728","article-title":"MPLUG-2: A modularized multi-modal foundation model across text, image and video","volume-title":"Proc. ICML","author":"Xu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3245608"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3163851"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110117"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25569"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3235367"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238314"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3367940"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76550-z"},{"key":"ref36","first-page":"1","article-title":"Object-CXR-automatic detection of foreign objects on chest X-rays","volume-title":"Proc. MIDL","author":"Healthcare"},{"key":"ref37","first-page":"1","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref38","first-page":"1","article-title":"How to adapt your large-scale vision-and-language model","volume-title":"Proc. ICLR","author":"Kim"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref41","article-title":"Exploring visual prompts for whole slide image classification with multiple instance learning","author":"Lin","year":"2023","journal-title":"arXiv:2303.13122"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01834"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00927"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01047"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3306105"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref51","first-page":"61","article-title":"P-tuning V2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","volume-title":"Proc. ACL-IJCNLP","author":"Liu"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02139"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01421"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref58","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023","journal-title":"arXiv:2303.12712"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3259010"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611967"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref62","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref64","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/10772323\/10570257.pdf?arnumber=10570257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T19:00:45Z","timestamp":1733252445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10570257\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":64,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2024.3418408","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}