{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T12:15:07Z","timestamp":1774008907595,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62125201"],"award-info":[{"award-number":["62125201"]}],"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":["62020106007"],"award-info":[{"award-number":["62020106007"]}],"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":["62176230"],"award-info":[{"award-number":["62176230"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3325965","type":"journal-article","created":{"date-parts":[[2023,10,19]],"date-time":"2023-10-19T18:15:01Z","timestamp":1697739301000},"page":"4706-4721","source":"Crossref","is-referenced-by-count":32,"title":["Multi-Task Paired Masking With Alignment Modeling for Medical Vision-Language Pre-Training"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9855-003X","authenticated-orcid":false,"given":"Ke","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5598-1692","authenticated-orcid":false,"given":"Yan","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0902-882X","authenticated-orcid":false,"given":"Hanliang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Regional Medical Center for National Institute of Respiratory Diseases, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2290-1785","authenticated-orcid":false,"given":"Jianping","family":"Fan","sequence":"additional","affiliation":[{"name":"AI Lab at Lenovo Research, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7227-3671","authenticated-orcid":false,"given":"Weidong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Medical Oncology, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University in Hangzhou, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref3","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref4","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_65"},{"key":"ref7","first-page":"1","article-title":"Advancing radiograph representation learning with masked record modeling","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zhou","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref10","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00425-9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01954"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.444"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2647386"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964326"},{"key":"ref17","article-title":"Vireo, TRECVID 2017: Video-to-text, ad-hoc video search and video hyperlinking","volume-title":"Proc. TREC Video Retrieval Eval.","author":"Nguyen","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3122542"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3125134"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3132724"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3273390"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3171661"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref36","first-page":"1","article-title":"Bilinear attention networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3529"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_26"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463584"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3185008"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105284"},{"key":"ref45","article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2019180041"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref49","first-page":"1","article-title":"Hybrid retrieval-generation reinforced agent for medical image report generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.90"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref54","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref55","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref56","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_7"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434063"},{"key":"ref59","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref61","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref62","first-page":"1","article-title":"Ul2: Unifying language learning paradigms","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Tay","year":"2023"},{"key":"ref63","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2017"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10288259.pdf?arnumber=10288259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:52:20Z","timestamp":1725904340000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10288259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3325965","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}