{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:31:56Z","timestamp":1779384716914,"version":"3.53.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"The Cancer Research Fund of Northern Sweden"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Med. Imaging"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1109\/tmi.2020.2978284","type":"journal-article","created":{"date-parts":[[2020,3,4]],"date-time":"2020-03-04T21:27:39Z","timestamp":1583357259000},"page":"2856-2868","source":"Crossref","is-referenced-by-count":70,"title":["A Question-Centric Model for Visual Question Answering in Medical Imaging"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2391-1419","authenticated-orcid":false,"given":"Minh H.","family":"Vu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7119-7646","authenticated-orcid":false,"given":"Tommy","family":"Lofstedt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tufve","family":"Nyholm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6791-4753","authenticated-orcid":false,"given":"Raphael","family":"Sznitman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv 1301 3781 [cs]"},{"key":"ref32","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref34","first-page":"1","article-title":"Statistical comparisons of classifiers over multiple data sets","volume":"7","author":"dem\u0161ar","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref10","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","author":"kim","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref12","first-page":"1","article-title":"Ensemble of streamlined bilinear visual question answering models for the Image-CLEF 2019 challenge in the medical domain","volume":"2380","author":"vu","year":"2019","journal-title":"Proc Working Notes of CLEF"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref15","first-page":"3294","article-title":"Skip-thought vectors","author":"kiros","year":"2015","journal-title":"Proc NIPS"},{"key":"ref16","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref17","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"arXiv 1906 08237"},{"key":"ref18","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref28","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1422953112"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00081"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28577-7_28"},{"key":"ref6","article-title":"VQA-Med: Overview of the medical visual question answering task at imageclef 2019","author":"abacha","year":"2019","journal-title":"Working Notes of CLEF"},{"key":"ref29","first-page":"1","article-title":"Automatic differentiation in Pytorch","author":"paszke","year":"2017","journal-title":"Proc NIPS-W"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32254-0_29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1181"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref22","first-page":"842","article-title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref21","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref24","first-page":"1482","article-title":"Bilinear classifiers for visual recognition","author":"pirsiavash","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref26","article-title":"BACH: Grand challenge on breast cancer histology images","author":"aresta","year":"2018","journal-title":"arXiv 1808 04277"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/data3030025"}],"container-title":["IEEE Transactions on Medical Imaging"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/42\/9181677\/09024133.pdf?arnumber=9024133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:59:14Z","timestamp":1651067954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9024133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9]]},"references-count":35,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tmi.2020.2978284","relation":{},"ISSN":["0278-0062","1558-254X"],"issn-type":[{"value":"0278-0062","type":"print"},{"value":"1558-254X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9]]}}}