{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:00:26Z","timestamp":1783530026466,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Ministry of Education, Singapore","award":["T2EP20222-0047"],"award-info":[{"award-number":["T2EP20222-0047"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589334.3648145","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"4575-4584","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Modularized Networks for Few-shot Hateful Meme Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9444-6913","authenticated-orcid":false,"given":"Rui","family":"Cao","sequence":"first","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1986-7750","authenticated-orcid":false,"given":"Roy Ka-Wei","family":"Lee","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3035-0074","authenticated-orcid":false,"given":"Jing","family":"Jiang","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Jean-Baptiste Alayrac Je? Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds Roman Ring Eliza Rutherford Serkan Cabi Tengda Han Zhitao Gong Sina Samangooei Marianne Monteiro Jacob L. Menick Sebastian Borgeaud Andy Brock Aida Nematzadeh Sahand Sharifzadeh Mikolaj Binkowski Ricardo Barreira Oriol Vinyals Andrew Zisserman and Kar\u00e9n Simonyan. 2022. Flamingo: a Visual Language Model for Few-Shot Learning. In NeurIPS."},{"key":"e_1_3_2_2_2_1","volume-title":"Shiori Sagawa, Jenia Jitsev, Simon Kornblith, Pang Wei Koh, Gabriel Ilharco, Mitchell Wortsman, and Ludwig Schmidt.","author":"Awadalla Anas","year":"2023","unstructured":"Anas Awadalla, Irena Gao, Josh Gardner, Jack Hessel, Yusuf Hanafy, Wanrong Zhu, Kalyani Marathe, Yonatan Bitton, Samir Yitzhak Gadre, Shiori Sagawa, Jenia Jitsev, Simon Kornblith, Pang Wei Koh, Gabriel Ilharco, Mitchell Wortsman, and Ludwig Schmidt. 2023. OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models. CoRR abs\/2308.01390 (2023)."},{"key":"e_1_3_2_2_3_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems.","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Je?rey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612498"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"e_1_3_2_2_6_1","article-title":"PaLM: Scaling Language Modeling with Pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez, Abhishek Rao, Parker Barnes, Yi Tay, Noam Shazeer, Vinodkumar Prabhakaran, Emily Reif, Nan Du, Ben Hutchinson, Reiner Pope, James Bradbury, Jacob Austin, Michael Isard, Guy Gur-Ari, Pengcheng Yin, Toju Duke, Anselm Levskaya, Sanjay Ghemawat, Sunipa Dev, Henryk Michalewski, Xavier Garcia, Vedant Misra, Kevin Robinson, Liam Fedus, Denny Zhou, Daphne Ippolito, David Luan, Hyeontaek Lim, Barret Zoph, Alexander Spiridonov, Ryan Sepassi, David Dohan, Shivani Agrawal, Mark Omernick, Andrew M. Dai, Thanumalayan Sankaranarayana Pillai, Marie Pellat, Aitor Lewkowycz, Erica Moreira, Rewon Child, Oleksandr Polozov, Katherine Lee, Zongwei Zhou, XuezhiWang, Brennan Saeta, Mark Diaz, Orhan Firat, Michele Catasta, Jason Wei, Kathy Meier-Hellstern, Douglas Eck, Je? Dean, Slav Petrov, and Noah Fiedel. 2023. PaLM: Scaling Language Modeling with Pathways. J. Mach. Learn. Res. 24 (2023), 240:1--240:113.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_2_7_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven C. H. Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven C. H. Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. CoRR abs\/2305.06500 (2023)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.semeval-1.74"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"e_1_3_2_2_11_1","volume-title":"Pruning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP. 4884--4896","author":"Guo Demi","year":"2021","unstructured":"Demi Guo, Alexander M. Rush, and Yoon Kim. 2021. Parameter-Efficient Transfer Learning with Di? Pruning. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP. 4884--4896."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICEC.1996.542381"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/665"},{"key":"e_1_3_2_2_14_1","unstructured":"Jordan Hoffmann Sebastian Borgeaud Arthur Mensch Elena Buchatskaya Trevor Cai Eliza Rutherford Diego de Las Casas Lisa Anne Hendricks Johannes Welbl Aidan Clark Tom Hennigan Eric Noland Katie Millican George van den Driessche Bogdan Damoc Aurelia Guy Simon Osindero Karen Simonyan Erich Elsen Jack W. Rae Oriol Vinyals and Laurent Sifre. 2022. Training Compute-Optimal Large Language Models. CoRR abs\/2203.15556 (2022)."},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ICML","volume":"97","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-Efficient Transfer Learning for NLP. In Proceedings of the 36th International Conference on Machine Learning, ICML, Vol. 97. 2790--2799."},{"key":"e_1_3_2_2_16_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR.","author":"Hu Edward J.","year":"2022","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In The Tenth International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_2_17_1","volume-title":"Tianyu Pang, Chao Du, and Min Lin.","author":"Huang Chengsong","year":"2023","unstructured":"Chengsong Huang, Qian Liu, Bill Yuchen Lin, Tianyu Pang, Chao Du, and Min Lin. 2023. LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition. CoRR abs\/2307.13269 (2023)."},{"key":"e_1_3_2_2_18_1","volume-title":"MemeCap: A Dataset for Captioning and Interpreting Memes. CoRR abs\/2305.13703","author":"Hwang EunJeong","year":"2023","unstructured":"EunJeong Hwang and Vered Shwartz. 2023. MemeCap: A Dataset for Captioning and Interpreting Memes. CoRR abs\/2305.13703 (2023)."},{"key":"e_1_3_2_2_19_1","unstructured":"Douwe Kiela Hamed Firooz Aravind Mohan Vedanuj Goswami Amanpreet Singh Pratik Ringshia and Davide Testuggine. 2020. The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes. In Advances in Neural Information Processing Systems NeurIPS."},{"key":"e_1_3_2_2_20_1","volume-title":"Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features. CoRR abs\/2210.05916","author":"Kumar Gokul Karthik","year":"2022","unstructured":"Gokul Karthik Kumar and Karthik Nandakumar. 2022. Hate-CLIPper: Multimodal Hateful Meme Classification based on Cross-modal Interaction of CLIP Features. CoRR abs\/2210.05916 (2022)."},{"key":"e_1_3_2_2_21_1","volume-title":"Disentangling Hate in Online Memes. In MM '21: ACM Multimedia Conference. ACM, 5138--5147","author":"Ka-Wei Lee Roy","year":"2021","unstructured":"Roy Ka-Wei Lee, Rui Cao, Ziqing Fan, Jing Jiang, and Wen-Haw Chong. 2021. Disentangling Hate in Online Memes. In MM '21: ACM Multimedia Conference. ACM, 5138--5147."},{"key":"e_1_3_2_2_22_1","volume-title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning. CoRR abs\/2305.03726","author":"Li Bo","year":"2023","unstructured":"Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Jingkang Yang, and Ziwei Liu. 2023. Otter: A Multi-Modal Model with In-Context Instruction Tuning. CoRR abs\/2305.03726 (2023)."},{"key":"e_1_3_2_2_23_1","volume-title":"International Conference on Machine Learning, ICML","volume":"202","author":"Li Junnan","year":"1973","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In International Conference on Machine Learning, ICML, Vol. 202. 19730--19742."},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP. 4582--4597","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Pre?x-Tuning: Optimizing Continuous Prompts for Generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP. 4582--4597."},{"key":"e_1_3_2_2_25_1","volume-title":"A Multimodal Framework for the Detection of Hateful Memes. arXiv preprint arXiv:2012.12871","author":"Lippe Phillip","year":"2020","unstructured":"Phillip Lippe, Nithin Holla, Shantanu Chandra, Santhosh Rajamanickam, Georgios Antoniou, Ekaterina Shutova, and Helen Yannakoudakis. 2020. A Multimodal Framework for the Detection of Hateful Memes. arXiv preprint arXiv:2012.12871 (2020)."},{"key":"e_1_3_2_2_26_1","volume-title":"Visual Instruction Tuning. CoRR abs\/2304.08485","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, QingyangWu, and Yong Jae Lee. 2023. Visual Instruction Tuning. CoRR abs\/2304.08485 (2023)."},{"key":"e_1_3_2_2_27_1","volume-title":"Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes. CoRR","author":"Niklas","year":"2020","unstructured":"Niklas Muennigho?. 2020. Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes. CoRR (2020). arXiv:2012.07788"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Shraman Pramanick Dimitar Dimitrov Rituparna Mukherjee Shivam Sharma Md. Shad Akhtar Preslav Nakov and Tanmoy Chakraborty. 2021. Detecting Harmful Memes and Their Targets. In Findings of the Association for Computational Linguistics: ACL\/IJCNLP. 2783--2796.","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.379"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1482"},{"key":"e_1_3_2_2_31_1","volume-title":"VL-ADAPTER: Parameter- Efficient Transfer Learning for Vision-and-Language Tasks. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 5217--5227","author":"Sung Yi-Lin","year":"2022","unstructured":"Yi-Lin Sung, Jaemin Cho, and Mohit Bansal. 2022. VL-ADAPTER: Parameter- Efficient Transfer Learning for Vision-and-Language Tasks. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 5217--5227."},{"key":"e_1_3_2_2_32_1","volume-title":"Training Neural Networks with Fixed Sparse Masks. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems. 24193--24205","author":"Sung Yi-Lin","year":"2021","unstructured":"Yi-Lin Sung, Varun Nair, and Colin Ra?el. 2021. Training Neural Networks with Fixed Sparse Masks. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems. 24193--24205."},{"key":"e_1_3_2_2_33_1","unstructured":"MosaicML NLP Team. 2023. Introducing MPT-7B: A New Standard for Open- Source Commercially Usable LLMs. www.mosaicml.com\/blog\/mpt-7b Accessed: 2023-05-05."},{"key":"e_1_3_2_2_34_1","volume-title":"Hoi","author":"Huat Tiong Anthony Meng","year":"2022","unstructured":"Anthony Meng Huat Tiong, Junnan Li, Boyang Li, Silvio Savarese, and Steven C. H. Hoi. 2022. Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training. In Findings of the Association for Computational Linguistics: EMNLP. 951--967."},{"key":"e_1_3_2_2_35_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. CoRR abs\/2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aur\u00e9lien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. CoRR abs\/2302.13971 (2023)."},{"key":"e_1_3_2_2_36_1","volume-title":"Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge. CoRR","author":"Velioglu Riza","year":"2020","unstructured":"Riza Velioglu and Jewgeni Rose. 2020. Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge. CoRR (2020). arXiv:2012.12975"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-2013"},{"key":"e_1_3_2_2_38_1","volume-title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language. In The Eleventh International Conference on Learning Representations, ICLR.","author":"Zeng Andy","year":"2023","unstructured":"Andy Zeng, Maria Attarian, Brian Ichter, Krzysztof Marcin Choromanski, Adrian Wong, Stefan Welker, Federico Tombari, Aveek Purohit, Michael S. Ryoo, Vikas Sindhwani, Johnny Lee, Vincent Vanhoucke, and Pete Florence. 2023. Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language. In The Eleventh International Conference on Learning Representations, ICLR."},{"key":"e_1_3_2_2_39_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona T. Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. CoRR abs\/2205.01068 (2022)."},{"key":"e_1_3_2_2_40_1","volume-title":"Conditional Prompt Learning for Vision-Language Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 16795--16804","author":"Zhou Kaiyang","year":"2022","unstructured":"Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2022. Conditional Prompt Learning for Vision-Language Models. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 16795--16804."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_2_42_1","volume-title":"Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution. CoRR","author":"Zhu Ron","year":"2020","unstructured":"Ron Zhu. 2020. Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution. CoRR (2020). arXiv:2012.08290"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3648145","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3648145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:28:53Z","timestamp":1755822533000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3648145"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":42,"alternative-id":["10.1145\/3589334.3648145","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3648145","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}