{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:22:23Z","timestamp":1780392143326,"version":"3.54.1"},"reference-count":78,"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"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada (NSERC) and Chittagong University of Engineering and Technology (CUET), Bangladesh","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3540388","type":"journal-article","created":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T18:35:11Z","timestamp":1739212511000},"page":"27570-27586","source":"Crossref","is-referenced-by-count":9,"title":["BVQA: Connecting Language and Vision Through Multimodal Attention for Open-Ended Question Answering"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3875-2526","authenticated-orcid":false,"given":"Md. Shalha Mucha","family":"Bhuyan","sequence":"first","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4575-0596","authenticated-orcid":false,"given":"Eftekhar","family":"Hossain","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0031-9284","authenticated-orcid":false,"given":"Khaleda Akhter","family":"Sathi","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8251-5168","authenticated-orcid":false,"given":"Md. Azad","family":"Hossain","sequence":"additional","affiliation":[{"name":"Department of Electronics and Telecommunication Engineering, Chittagong University of Engineering and Technology, Chattogram, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6347-7509","authenticated-orcid":false,"given":"M. Ali Akber","family":"Dewan","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Faculty of Science and Technology, Athabasca University, Athabasca, AB, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref2","article-title":"A comprehensive survey on cross-modal retrieval","author":"Wang","year":"2016","journal-title":"arXiv:1607.06215"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.06.005"},{"key":"ref6","article-title":"MMFT-BERT: Multimodal fusion transformer with BERT encodings for visual question answering","author":"Khan","year":"2020","journal-title":"arXiv:2010.14095"},{"key":"ref7","article-title":"Multimodal learning and reasoning for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Ilievski"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.93"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_34"},{"key":"ref12","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.dravidianlangtech-1.3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.90"},{"key":"ref15","article-title":"A review of Bangla natural language processing tasks and the utility of transformer models","author":"Alam","year":"2021","journal-title":"arXiv:2107.03844"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT57492.2022.10055205"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3530190.3534837"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref20","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref21","article-title":"Negative object presence evaluation (NOPE) to measure object hallucination in vision-language models","author":"Lovenia","year":"2023","journal-title":"arXiv:2310.05338"},{"key":"ref22","article-title":"Evaluation and analysis of hallucination in large vision-language models","author":"Wang","year":"2023","journal-title":"arXiv:2308.15126"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.646"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02083"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43427-3_35"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00143"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00648"},{"key":"ref30","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":"ref31","article-title":"Exploring models and data for image question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.001"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00522"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"issue":"6","key":"ref38","first-page":"1","article-title":"VQA-med: Overview of the medical visual question answering task at ImageCLEF 2019","volume-title":"Proc. CLEF","volume":"2","author":"Abacha"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.90"},{"key":"ref40","first-page":"1918","article-title":"Visual question answering dataset for bilingual image understanding: A study of cross-lingual transfer using attention maps","volume-title":"Proc. 27th Int. Conf. Comput. Linguistics","author":"Shimizu"},{"key":"ref41","first-page":"683","article-title":"ViVQA: Vietnamese visual question answering","volume-title":"Proc. 35th Pacific Asia Conf. Lang., Inf. Comput.","author":"Tran"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref43","article-title":"Image question answering: A visual semantic embedding model and a new dataset","author":"Ren","year":"2015","journal-title":"arXiv:1505.02074"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref45","article-title":"ABC-CNN: An attention based convolutional neural network for visual question answering","author":"Chen","year":"2015","journal-title":"arXiv:1511.05960"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref47","article-title":"A focused dynamic attention model for visual question answering","author":"Ilievski","year":"2016","journal-title":"arXiv:1604.01485"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1044"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref51","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Lu"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-024-09818-4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3605423.3605427"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120"},{"key":"ref57","article-title":"MultiModal-GPT: A vision and language model for dialogue with humans","author":"Gong","year":"2023","journal-title":"arXiv:2305.04790"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.06.100"},{"key":"ref60","article-title":"A technique for the measurement of attitudes","author":"Likert","year":"1932","journal-title":"Arch. Psychol."},{"key":"ref61","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref63","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref65","author":"Sarker","year":"2020","journal-title":"Banglabert: Bengali Mask Language Model for Bengali Language Understanding"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3465055"},{"key":"ref68","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-17162-3"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref71","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128730"},{"key":"ref73","first-page":"13028","article-title":"MCLIP: Multilingual CLIP via cross-lingual transfer","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics","author":"Chen"},{"key":"ref74","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref75","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref77","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref78","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10878995.pdf?arnumber=10878995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T18:57:11Z","timestamp":1739991431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10878995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3540388","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}