{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:13:04Z","timestamp":1774627984935,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171377"],"award-info":[{"award-number":["62171377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92470101"],"award-info":[{"award-number":["92470101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ningbo Clinical Research Center for Medical Imaging","award":["2021L003"],"award-info":[{"award-number":["2021L003"]}]},{"name":"Ningbo Clinical Research Center for Medical Imaging","award":["2022LYKFZD06"],"award-info":[{"award-number":["2022LYKFZD06"]}]},{"DOI":"10.13039\/501100001809","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["JCYJ20220530161616036"],"award-info":[{"award-number":["JCYJ20220530161616036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tmi.2025.3580561","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T13:40:32Z","timestamp":1750167632000},"page":"4605-4616","source":"Crossref","is-referenced-by-count":3,"title":["Bridging the Semantic Gap in Medical Visual Question Answering With Prompt Learning"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2437-283X","authenticated-orcid":false,"given":"Zilin","family":"Lu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5229-2709","authenticated-orcid":false,"given":"Qingjie","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5679-1761","authenticated-orcid":false,"given":"Mengkang","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8350-6581","authenticated-orcid":false,"given":"Geng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9273-2847","authenticated-orcid":false,"given":"Yong","family":"Xia","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.07.160"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72086-4_61"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-18814-5_1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-bioeng071516-044442"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01504"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02328-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2025.3556310"},{"key":"ref9","article-title":"Overview of ImageCLEF 2018 medical domain visual question answering task","volume-title":"Proc. CLEF (Working Notes)","author":"Hasan"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3185008"},{"key":"ref14","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":"ref15","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref16","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref17","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref23","article-title":"How much can CLIP benefit vision-and-language tasks?","author":"Shen","year":"2021","journal-title":"arXiv:2107.06383"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref26","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref31","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI53787.2023.10230743"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3327962"},{"key":"ref41","article-title":"Visual prompt tuning for test-time domain adaptation","author":"Gao","year":"2022","journal-title":"arXiv:2210.04831"},{"key":"ref42","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref44","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2021","journal-title":"arXiv:2111.06377"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.191"},{"key":"ref47","article-title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","author":"Johnson","year":"2019","journal-title":"arXiv:1901.07042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref51","first-page":"1571","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Kim"},{"key":"ref52","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548122"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3232411"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103464"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3325965"},{"key":"ref58","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/42\/11230061\/11039185.pdf?arnumber=11039185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:53:38Z","timestamp":1762455218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11039185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":58,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2025.3580561","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}