{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T06:11:30Z","timestamp":1757571090909,"version":"3.33.0"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"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":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825179","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"1814-1823","source":"Crossref","is-referenced-by-count":1,"title":["SparrowVQE: Visual Question Explanation for Course Content Understanding"],"prefix":"10.1109","author":[{"given":"Jialu","family":"Li","sequence":"first","affiliation":[{"name":"Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manish Kumar","family":"Thota","sequence":"additional","affiliation":[{"name":"Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruslan","family":"Gokhman","sequence":"additional","affiliation":[{"name":"Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radek","family":"Holik","sequence":"additional","affiliation":[{"name":"Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youshan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Yeshiva University,Artificial Intelligence,Graduate Computer Science and Engineering Department,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.09.008"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-2594097\/v1","article-title":"Eduvi: An educational-based visual question answering and image captioning system for enhancing the knowledge of primary level students","author":"Gupta","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAE.2017.8291426"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICESC51422.2021.9532611"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3991\/ijet.v18i22.44103"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5573\/IEIESPC.2023.12.5.419"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ITCA52113.2020.00069"},{"key":"ref9","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","volume":"27","author":"Malinowski","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0966-6"},{"article-title":"Visual question answering: A survey on techniques and common trends in recent literature","year":"2023","author":"de Faria","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.387"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/biomedinformatics4010004"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102346"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"article-title":"Overview of the vqa-med task at imageclef 2021: Visual question answering and generation in the medical domain","volume-title":"Proceedings of the CLEF 2021 Conference and Labs of the Evaluation Forum-working notes. 21-24 September 2021","author":"Abacha","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.251"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15181-1_6"},{"article-title":"Muvam: A multi-view attention-based model for medical visual question answering","year":"2021","author":"Pan","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00536"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref25"},{"article-title":"Visual instruction tuning","volume-title":"NeurIPS","author":"Liu","key":"ref26"},{"article-title":"Pix2struct: Screenshot parsing as pretraining for visual language understanding","year":"2023","author":"Lee","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"volume-title":"Pymupdf","year":"2023","key":"ref29"},{"year":"2023","key":"ref30","article-title":"Silero speech-to-text models"},{"year":"2023","key":"ref31","article-title":"Silero models: Pretrained enterprise-grade stt models"},{"key":"ref32","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"CoRR"},{"volume-title":"Google cloud speech-to-text api","year":"2023","key":"ref33"},{"volume-title":"Cockatoo: Online transcription service","year":"2023","key":"ref34"},{"year":"2023","key":"ref35","article-title":"Ai-powered speech recognition"},{"year":"2023","key":"ref36","article-title":"Automated transcription software"},{"volume-title":"Parrot: Online transcripts","year":"2023","key":"ref37"},{"volume-title":"Veed.io: Simple online video editing","year":"2023","key":"ref38"},{"volume-title":"Speechtext: Fast and accurate audio transcription service","year":"2023","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"article-title":"A simple framework for contrastive learning of visual representations","year":"2020","author":"Chen","key":"ref43"},{"article-title":"Improved baselines with momentum contrastive learning","year":"2020","author":"Chen","key":"ref44"},{"article-title":"Textbooks are all you need ii: phi-1.5 technical report","year":"2023","author":"Li","key":"ref45"},{"article-title":"Improved baselines with visual instruction tuning","year":"2023","author":"Liu","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","year":"2016","author":"Krishna","key":"ref48"},{"article-title":"Rouge 2.0: Updated and improved measures for evaluation of summarization tasks","year":"2018","author":"Ganesan","key":"ref49"},{"key":"ref50","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL \u201802","author":"Papineni"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179544"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CITSM.2016.7577578"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.792"},{"article-title":"Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices","year":"2023","author":"Chu","key":"ref57"},{"article-title":"Rethinking visual prompting for multi-modal large language models with external knowledge","year":"2024","author":"Lin","key":"ref58"},{"article-title":"Tinygpt-v: Efficient multimodal large language model via small backbones","year":"2023","author":"Yuan","key":"ref59"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825179.pdf?arnumber=10825179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:45:58Z","timestamp":1737099958000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825179","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}