{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:40:32Z","timestamp":1763343632209,"version":"3.45.0"},"reference-count":35,"publisher":"Tech Science Press","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.064734","type":"journal-article","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T03:50:57Z","timestamp":1746762657000},"page":"1863-1882","source":"Crossref","is-referenced-by-count":0,"title":["Low-Rank Adapter Layers and Bidirectional Gated Feature Fusion for Multimodal Hateful Memes Classification"],"prefix":"10.32604","volume":"84","author":[{"given":"Youwei","family":"Huang","sequence":"first","affiliation":[]},{"given":"Han","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"Cheng","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Yijie","family":"Peng","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"12833","DOI":"10.1007\/s10462-023-10459-7","article-title":"Detecting hate speech in memes: a review","volume":"56","author":"de Hermida","year":"2023","journal-title":"Artif Intell Rev"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"Hossain E, Sharif O, Hoque MM, Preum SM. Deciphering hate: identifying hateful memes and their targets. arXiv:2403.10829. 2024.","DOI":"10.18653\/v1\/2024.acl-long.454"},{"key":"ref3","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021 Jul 18\u201324"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","article-title":"Clip-adapter: better vision-language models with feature adapters","volume":"132","author":"Gao","year":"2024","journal-title":"Int J Comput Vis"},{"key":"ref5","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2023","first-page":"10899","article-title":"Task residual for tuning vision-language models","author":"Yu","year":"2023 Jun 17\u201324"},{"key":"ref6","series-title":"2022 European Conference on Computer Vision","first-page":"493","article-title":"Tip-adapter: training-free adaption of clip for few-shot classification","author":"Zhang","year":"2022 Oct 23\u201327"},{"key":"ref7","series-title":"Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision","first-page":"2832","article-title":"Mapping memes to words for multimodal hateful meme classification","author":"Burbi","year":"2023 Oct 2\u20136"},{"key":"ref8","first-page":"2611","article-title":"The hateful memes challenge: detecting hate speech in multimodal memes","volume":"33","author":"Kiela","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"Long HW, Li H, Cai W. CoinCLIP: a multimodal framework for evaluating the viability of memecoins in the Web3 ecosystem. arXiv:2412.07591. 2024.","DOI":"10.1145\/3746252.3760881"},{"key":"ref10","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, et al. Lora: low-rank adaptation of large language models. arXiv:2106.09685. 2021."},{"key":"ref11","first-page":"1022","article-title":"Compacter: efficient low-rank hypercomplex adapter layers","volume":"34","author":"Karimi Mahabadi","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref12","series-title":"Proceedings of the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events From Text (CASE 2024)","first-page":"73","article-title":"CLTL@ Multimodal hate speech event detection 2024: the winning approach to detecting multimodal hate speech and its targets","author":"Wang","year":"2024"},{"key":"ref13","unstructured":"Loureiro D, Rezaee K, Riahi T, Barbieri F, Neves L, Anke LE, et al. Tweet insights: a visualization platform to extract temporal insights from twitter. arXiv:2308.02142. 2023."},{"key":"ref14","series-title":"Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12009","article-title":"Swin transformer v2: scaling up capacity and resolution","author":"Liu","year":"2022 Jun 18\u201324"},{"key":"ref15","series-title":"8th ICML Workshop on Automated Machine Learning (AutoML)","first-page":"1","article-title":"Multimodal automl on structured tables with text fields","author":"Shi","year":"2021"},{"key":"ref16","series-title":"Proceedings of the 2020 IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"1470","article-title":"Exploring hate speech detection in multimodal publications","author":"Gomez","year":"2020 Mar 1\u20135"},{"key":"ref17","series-title":"Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016 Jun 27\u201330"},{"key":"ref18","unstructured":"Velioglu R, Rose J. Detecting hate speech in memes using multimodal deep learning approaches: prize-winning solution to hateful memes challenge. arXiv:2012.12975. 2020."},{"key":"ref19","unstructured":"Li LH, Yatskar M, Yin D, Hsieh CJ, Chang KW. Visualbert: a simple and performant baseline for vision and language. arXiv:1908.03557. 2019."},{"key":"ref20","series-title":"Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision","first-page":"15338","article-title":"Zero-shot composed image retrieval with textual inversion","author":"Baldrati","year":"2023 Oct 2\u20136 2023"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"Mei J, Chen J, Lin W, Byrne B, Tomalin M. Improving hateful meme detection through retrieval-guided contrastive learning. arXiv:2311.08110. 2023.","DOI":"10.18653\/v1\/2024.acl-long.291"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"Shah SB, Shiwakoti S, Chaudhary M, Wang H. Memeclip: leveraging clip representations for multimodal meme classification. arXiv:2409.14703. 2024.","DOI":"10.18653\/v1\/2024.emnlp-main.959"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int J Comput Vis"},{"key":"ref24","unstructured":"Chen G, Yao W, Song X, Li X, Rao Y, Zhang K. Plot: prompt learning with optimal transport for vision-language models. arXiv:2210.01253. 2022."},{"key":"ref25","unstructured":"Lippe P, Holla N, Chandra S, Rajamanickam S, Antoniou G, Shutova E, et al. A multimodal framework for the detection of hateful memes. arXiv:2012.12871. 2020."},{"key":"ref26","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref27","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4171","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019 Jun 2\u20137"},{"key":"ref28","series-title":"Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages","first-page":"352","article-title":"Codewithzichao@ DravidianLangTech-EACL2021: exploring multimodal transformers for meme classification in Tamil language","author":"Li","year":"2021"},{"key":"ref29","series-title":"Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016 Jun 27\u201330"},{"key":"ref30","doi-asserted-by":"crossref","unstructured":"Conneau A, Khandelwal K, Goyal N, Chaudhary V, Wenzek G, Guzm\u00e1n F, et al. Unsupervised cross-lingual representation learning at scale. arXiv:1911.02116. 2019.","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"Pramanick S, Sharma S, Dimitrov D, Akhtar MS, Nakov P, Chakraborty T. MOMENTA: a multimodal framework for detecting harmful memes and their targets. arXiv:2109.05184. 2021.","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"ref32","doi-asserted-by":"crossref","unstructured":"Kumar GK, Nandakumar K. Hate-CLIPper: multimodal hateful meme classification based on cross-modal interaction of CLIP features. arXiv:2210.05916. 2022.","DOI":"10.18653\/v1\/2022.nlp4pi-1.20"},{"key":"ref33","doi-asserted-by":"crossref","unstructured":"Hossain E, Sharif O, Hoque MM, Preum SM. Align before attend: aligning visual and textual features for multimodal hateful content detection. arXiv:2402.09738. 2024.","DOI":"10.18653\/v1\/2024.eacl-srw.12"},{"key":"ref34","doi-asserted-by":"crossref","unstructured":"Pramanick S, Dimitrov D, Mukherjee R, Sharma S, Akhtar MS, Nakov P, et al. Detecting harmful memes and their targets. arXiv:2110.00413. 2021.","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"ref35","series-title":"Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21466","article-title":"Effective conditioned and composed image retrieval combining clip-based features","author":"Baldrati","year":"2022 Jun 18\u201324"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-84-1\/TSP_CMC_64734\/TSP_CMC_64734.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T01:36:18Z","timestamp":1763343378000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v84n1\/61770"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.064734","relation":{},"ISSN":["1546-2226"],"issn-type":[{"type":"electronic","value":"1546-2226"}],"subject":[],"published":{"date-parts":[[2025]]}}}