{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T04:14:51Z","timestamp":1772770491134,"version":"3.50.1"},"reference-count":11,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,4,13]],"date-time":"2021-04-13T00:00:00Z","timestamp":1618272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,13]],"date-time":"2021-04-13T00:00:00Z","timestamp":1618272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,13]],"date-time":"2021-04-13T00:00:00Z","timestamp":1618272000000},"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":[[2021,4,13]]},"DOI":"10.1109\/isbi48211.2021.9434063","type":"proceedings-article","created":{"date-parts":[[2021,5,25]],"date-time":"2021-05-25T20:14:15Z","timestamp":1621973655000},"page":"1033-1036","source":"Crossref","is-referenced-by-count":122,"title":["MMBERT: Multimodal BERT Pretraining for Improved Medical VQA"],"prefix":"10.1109","author":[{"given":"Yash","family":"Khare","sequence":"first","affiliation":[]},{"given":"Viraj","family":"Bagal","sequence":"additional","affiliation":[]},{"given":"Minesh","family":"Mathew","sequence":"additional","affiliation":[]},{"given":"Adithi","family":"Devi","sequence":"additional","affiliation":[]},{"given":"U Deva","family":"Priyakumar","sequence":"additional","affiliation":[]},{"given":"CV","family":"Jawahar","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","article-title":"UNITER: Universal image-text representation learning","author":"yen-chun","year":"2020","journal-title":"ECCV"},{"key":"ref3","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2980024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"ref5","article-title":"Zhejiang university at ImageCLEF 2019 visual question answering in the medical domain","author":"yan","year":"2019","journal-title":"CLEF (Working Notes)"},{"key":"ref8","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"ref2","article-title":"VQA-Med: Overview of the Medical Visual Question Answering Task at ImageCLEF 2019","author":"abacha","year":"0","journal-title":"CLEF 2019 Working Notes 2019 CEUR Workshop Proceedings"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"}],"event":{"name":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","location":"Nice, France","start":{"date-parts":[[2021,4,13]]},"end":{"date-parts":[[2021,4,16]]}},"container-title":["2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9433749\/9433753\/09434063.pdf?arnumber=9434063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:47Z","timestamp":1652197307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9434063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,13]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/isbi48211.2021.9434063","relation":{},"subject":[],"published":{"date-parts":[[2021,4,13]]}}}