{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T22:10:41Z","timestamp":1784239841384,"version":"3.55.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228425","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["Efficient Bilinear Attention-based Fusion for Medical Visual Question Answering"],"prefix":"10.1109","author":[{"given":"Zhilin","family":"Zhang","sequence":"first","affiliation":[{"name":"New York University,Tandon School of Engineering,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongji University,College of Electronic and Information Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanghao","family":"Qin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiqi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tongji University,College of Electronic and Information Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoliang","family":"Gong","sequence":"additional","affiliation":[{"name":"Tongji University,College of Electronic and Information Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_57"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_20"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.285"},{"key":"ref10","article-title":"Bilinear attention networks","volume":"31","author":"Kim","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_40"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-34048-2_34"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1056\/aioa2400640"},{"key":"ref18","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3021128"},{"key":"ref21","article-title":"Hierarchical question-image co-attention for visual question answering","volume":"29","author":"Lu","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413761"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.88"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228425.pdf?arnumber=11228425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T21:46:57Z","timestamp":1784238417000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228425","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}