{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:55:55Z","timestamp":1766138155707,"version":"3.37.3"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956469","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"1712-1718","source":"Crossref","is-referenced-by-count":6,"title":["A Transformer-based Medical Visual Question Answering Model"],"prefix":"10.1109","author":[{"given":"Lei","family":"Liu","sequence":"first","affiliation":[{"name":"Inner Mongolia University,College of Computer Science,Hohhot,China"}]},{"given":"Xiangdong","family":"Su","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,College of Computer Science,Hohhot,China"}]},{"given":"Hui","family":"Guo","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,College of Computer Science,Hohhot,China"}]},{"given":"Daobin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,College of Computer Science,Hohhot,China"}]}],"member":"263","reference":[{"key":"ref10","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"mixup: Beyond empirical risk minimization","year":"2017","author":"zhang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref17","article-title":"Bilinear attention networks","volume":"31","author":"kim","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463584"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation","year":"2021","author":"cao","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_20"},{"article-title":"Deformable detr: Deformable transformers for end-to-end object detection","year":"2020","author":"zhu","key":"ref8"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"dosovitskiy","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"ref9","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"kim","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"article-title":"Fixing weight decay regularization in adam","year":"2018","author":"loshchilov","key":"ref22"},{"key":"ref21","article-title":"Vqa-med: Overview of the medical visual question answering task at imageclef 2019","volume":"2","author":"abacha","year":"2019","journal-title":"CLEF (Working Notes)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.3115\/v1\/D14-1162","article-title":"Glove: Global vectors for word representation","author":"pennington","year":"2014","journal-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref25"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","start":{"date-parts":[[2022,8,21]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956469.pdf?arnumber=9956469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:04:05Z","timestamp":1671480245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956469","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}