{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:59:24Z","timestamp":1781726364095,"version":"3.54.5"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Bangladesh University of Business and Technology (BUBT) Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tai.2025.3623093","type":"journal-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:59:41Z","timestamp":1760983181000},"page":"2726-2738","source":"Crossref","is-referenced-by-count":2,"title":["Co-AttenDWG: Coattentive Dimension-Wise Gating and Expert Fusion for Multimodal Offensive Content Detection"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4883-1802","authenticated-orcid":false,"given":"Md. Mithun","family":"Hossain","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1584-3282","authenticated-orcid":false,"given":"Md. Shakil","family":"Hossain","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7286-6722","authenticated-orcid":false,"given":"Sudipto","family":"Chaki","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5738-1631","authenticated-orcid":false,"given":"M. F.","family":"Mridha","sequence":"additional","affiliation":[{"name":"Department of Computer Science, American International University-Bangladesh, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref2","first-page":"689","article-title":"Multimodal deep learning","volume-title":"Proc. ICML","volume":"11","author":"Ngiam","year":"2011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2025.3544263"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2024.3430821"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-4007"},{"key":"ref9","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Krizhevsky","year":"2012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref12","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref14","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref15","article-title":"Uniter: Learning universal image-text representations","author":"Chen","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3718381"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i20.30213"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12163504"},{"key":"ref21","article-title":"Supervised multimodal bitransformers for classifying images and text","author":"Kiela","year":"2019"},{"key":"ref22","first-page":"2022","article-title":"Emotion based hate speech detection using multimodal learning","author":"Rana"},{"key":"ref23","article-title":"Multimodal datasets: Misogyny, pornography, and malignant stereotypes","author":"Birhane","year":"2021"},{"key":"ref24","first-page":"32","article-title":"Multimodal meme dataset (multioff) for identifying offensive content in image and text","volume-title":"Proc. 2nd Workshop Trolling, Aggression Cyberbullying","author":"Suryawanshi","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3713077"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3709147"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.01.019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3219229"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122728"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103193"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3652504"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.02.028"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc7040164"},{"key":"ref35","article-title":"Syntax-aware hybrid prompt model for few-shot multi-modal sentiment analysis","author":"Zhou","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3280952"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06602-y"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13112069"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3380375"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref42","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017"},{"key":"ref43","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref44","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref45","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref46","article-title":"EfficientNetv2: Smaller models and faster training","volume-title":"Proc. ICML","author":"Tan","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref48","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (PmLR)","author":"Radford","year":"2021"},{"key":"ref49","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref50","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","year":"2022"},{"key":"ref51","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Li","year":"2023"},{"key":"ref52","article-title":"QWEN2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref54","article-title":"Task report: Memotion analysis 1.0@ semeval 2020: The visuo-lingual metaphor","volume-title":"Proc. 14th Int. Workshop Semantic Eval. (SemEval-2020)","author":"Sharma","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3656169"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11503071\/11207235.pdf?arnumber=11207235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T19:42:04Z","timestamp":1781725324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11207235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":55,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3623093","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}