{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:02:46Z","timestamp":1775836966996,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"King Saud University, Riyadh, Saudi Arabia, for funding this research through Researchers Supporting Project","award":["RSP2024R260"],"award-info":[{"award-number":["RSP2024R260"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3505614","type":"journal-article","created":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T18:49:07Z","timestamp":1732560547000},"page":"177811-177828","source":"Crossref","is-referenced-by-count":9,"title":["MemesViTa: A Novel Multimodal Fusion Technique for Troll Memes Identification"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8607-0386","authenticated-orcid":false,"given":"Tipu","family":"Sultan","sequence":"first","affiliation":[{"name":"Department of Aerospace and Mechanical Engineering, Saint Louis University, St. Louis, MO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0640-1425","authenticated-orcid":false,"given":"Mohammad Abu Tareq","family":"Rony","sequence":"additional","affiliation":[{"name":"Department of Statistics, Noakhali Science and Technology University, Noakhali, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammad Shariful","family":"Islam","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Telecommunication Engineering, Noakhali Science and Technology University, Noakhali, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6168-4141","authenticated-orcid":false,"given":"Saad","family":"Aldosary","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Community College, King Saud University, Riyadh, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7509-2120","authenticated-orcid":false,"given":"Walid","family":"El-Shafai","sequence":"additional","affiliation":[{"name":"Department of Electronics and Electrical Communications Engineering, Faculty of Electronic Engineering, Menoufia University, Menouf, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016949"},{"issue":"8","key":"ref2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref4","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref5","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kiela"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1108\/AJIM-07-2023-0239","article-title":"Multimodal archive resources organization based on deep learning: A prospective framework","author":"Zhou","year":"2024","journal-title":"Aslib J. Inf. Manage."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.15041"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.dravidianlangtech-1.27"},{"key":"ref9","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.025"},{"key":"ref13","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":"ref14","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512260"},{"key":"ref16","article-title":"Detecting and correcting hate speech in multimodal memes with large visual language model","author":"Van","year":"2023","journal-title":"arXiv:2311.06737"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455994"},{"key":"ref18","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tsimpoukelli"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645381"},{"key":"ref20","article-title":"GOAT-Bench: Safety insights to large multimodal models through meme-based social abuse","author":"Lin","year":"2024","journal-title":"arXiv:2401.01523"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCS52333.2021.9497374"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3623396"},{"key":"ref25","article-title":"Detecting hate speech in memes using multimodal deep learning approaches: Prize-winning solution to hateful memes challenge","author":"Velioglu","year":"2020","journal-title":"arXiv:2012.12975"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2024.200399"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IS61756.2024.10705175"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ETFG55873.2023.10407265"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3428918"},{"key":"ref32","article-title":"Language models are few-shot learners","author":"Mann","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref33","first-page":"1542","article-title":"MemoSen: A multimodal dataset for sentiment analysis of memes","volume-title":"Proc. 13th Lang. Resour. Eval. Conf.","author":"Hossain"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-00966-y"},{"key":"ref35","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref36","article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","author":"He","year":"2020","journal-title":"arXiv:2006.03654"},{"key":"ref37","article-title":"Exploiting cloze questions for few shot text classification and natural language inference","author":"Schick","year":"2020","journal-title":"arXiv:2001.07676"},{"key":"ref38","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv:1910.01108"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.l803.03635"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3007"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10766576.pdf?arnumber=10766576","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:11:55Z","timestamp":1733883115000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10766576\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3505614","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}