{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T18:44:02Z","timestamp":1754160242795,"version":"3.41.2"},"reference-count":64,"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\/100009122","name":"Institutional Fund Projects","doi-asserted-by":"publisher","award":["IFPIP: 1176-611-1443"],"award-info":[{"award-number":["IFPIP: 1176-611-1443"]}],"id":[{"id":"10.13039\/100009122","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Education and Deanship of Scientific Research (DSR), King Abdulaziz University (KAU), Jeddah, Saudi Arabia"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3586505","type":"journal-article","created":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:20:23Z","timestamp":1752103223000},"page":"125090-125100","source":"Crossref","is-referenced-by-count":0,"title":["Dual-Branch Neural Network for Bridging Semantic Gap in Harmful Meme Detection"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9046-1502","authenticated-orcid":false,"given":"Muhammad","family":"Shoib Amin","sequence":"first","affiliation":[{"name":"School of Internet of Things Engineering, Wuxi University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0655-8414","authenticated-orcid":false,"given":"Summaira","family":"Jabeen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8081-6530","authenticated-orcid":false,"given":"Ahmad A.","family":"Alzahrani","sequence":"additional","affiliation":[{"name":"Faculty of Computing and Information Technology, King Abdulaziz University, Rabigh, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1164-3103","authenticated-orcid":false,"given":"Abdolraheem","family":"Khader","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8944-8922","authenticated-orcid":false,"given":"Ali","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Faculty of Computing and Information Technology, King Abdulaziz University, Rabigh, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8054-6107","authenticated-orcid":false,"given":"Sadaf","family":"Hussain","sequence":"additional","affiliation":[{"name":"Department of Information Technology, Lahore Garrison University, Lahore, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i12.33426"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3649447"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3545572"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.vrih.2023.06.003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.vrih.2023.06.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00061"},{"key":"ref8","first-page":"852","article-title":"Multimodal named entity recognition for short social media posts","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Moon"},{"key":"ref9","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kiela"},{"key":"ref10","first-page":"4439","article-title":"MOMENTA: A multimodal framework for detecting harmful memes and their targets","volume-title":"Proc. Findings Assoc. Comput. Linguistics, EMNLP","author":"Pramanick"},{"key":"ref11","first-page":"344","article-title":"The hateful memes challenge: Competition report","volume-title":"Proc. NeurIPS Competition Demonstration Track","author":"Kiela"},{"key":"ref12","article-title":"A survey on multimodal disinformation detection","author":"Alam","year":"2021","journal-title":"arXiv:2103.12541"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v15i1.18080"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.99"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3384025"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3648146"},{"key":"ref17","first-page":"13302","article-title":"Towards comprehensive detection of Chinese harmful memes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645381"},{"key":"ref19","first-page":"126","article-title":"Findings of the shared task on troll meme classification in Tamil","volume-title":"Proc. 1st Workshop Speech Lang. Technol. Dravidian Lang.","author":"Suryawanshi"},{"key":"ref20","article-title":"Detecting and understanding harmful memes: A survey","author":"Sharma","year":"2022","journal-title":"arXiv:2205.04274"},{"key":"ref21","first-page":"32","article-title":"Multimodal meme dataset (MultiOFF) for identifying offensive content in image and text","volume-title":"Proc. 2nd Workshop Trolling","author":"Suryawanshi"},{"key":"ref22","first-page":"7","article-title":"A dataset for troll classification of tamilmemes","volume-title":"Proc. 5th Workshop Indian Lang. Data, Resources Eval.","author":"Suryawanshi"},{"key":"ref23","article-title":"Supervised multimodal bitransformers for classifying images and text","author":"Kiela","year":"2019","journal-title":"arXiv:1909.02950"},{"key":"ref24","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref25","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref27","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"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612498"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3587427"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116209"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3223683"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03723-6"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03585-y"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03563-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.326"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.13"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747704"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688978"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3640457.3688138"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2021.1995073"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18575-4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097207"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00184"},{"article-title":"Multimodal representation and learning","year":"2019","author":"Nawaz","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612857"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11945"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03546-5"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1117\/12.2680761"},{"key":"ref52","article-title":"Modality invariant multimodal learning to handle missing modalities: A single-branch approach","author":"Saad Saeed","year":"2024","journal-title":"arXiv:2408.07445"},{"key":"ref53","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":"ref54","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NaacL-HLT","author":"Devlin"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref56","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859654"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(00)00115-4"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-025-00370-y"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11075735.pdf?arnumber=11075735","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T06:30:13Z","timestamp":1753511413000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11075735\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3586505","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}