{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:33:36Z","timestamp":1781109216498,"version":"3.54.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3572529","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T18:06:23Z","timestamp":1747937183000},"page":"93453-93467","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing Visual Question Answering for Multiple Choice Questions"],"prefix":"10.1109","volume":"13","author":[{"given":"Rashi","family":"Goel","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harsh","family":"Nandwani","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eshaan","family":"Shah","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7888-6516","authenticated-orcid":false,"given":"Ashalatha","family":"Nayak","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7671-6633","authenticated-orcid":false,"given":"Archana","family":"Praveen Kumar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102270"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3366154"},{"key":"ref6","article-title":"Visual question answering: A survey on techniques and common trends in recent literature","author":"de Faria","year":"2023","journal-title":"arXiv:2305.11033"},{"key":"ref7","first-page":"1","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Malinowski"},{"key":"ref8","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref10","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref11","first-page":"1","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Gao"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1422953112"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","article-title":"ABC-CNN: An attention based convolutional neural network for visual question answering","author":"Chen","year":"2015","journal-title":"arXiv:1511.05960"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref18","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.344"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00851"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.07.015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref24","first-page":"1","article-title":"Exploring models and data for image question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref26","article-title":"OpenImages: A public dataset for large-scale multi-label and multi-class image classification","author":"Krasin","year":"2017","journal-title":"Dataset"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1093\/mnras\/stz1870"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00280"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ITCA52113.2020.00069"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018876"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220036"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"ref45","article-title":"VQA and visual reasoning: An overview of recent datasets, methods and challenges","author":"Zakari","year":"2022","journal-title":"arXiv:2212.13296"},{"key":"ref46","first-page":"3489","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Dosovitskiy"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/s21248309"},{"key":"ref51","first-page":"1686","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics","author":"Devlin"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11009180.pdf?arnumber=11009180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T05:53:48Z","timestamp":1748930028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11009180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3572529","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}