{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:00:24Z","timestamp":1783530024850,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612498","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"5244-5252","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":49,"title":["Pro-Cap: Leveraging a Frozen Vision-Language Model for 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\/0000-0002-6328-5889","authenticated-orcid":false,"given":"Ming Shan","family":"Hee","sequence":"additional","affiliation":[{"name":"Singapore University of Design and Technology, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5190-2534","authenticated-orcid":false,"given":"Adriel","family":"Kuek","sequence":"additional","affiliation":[{"name":"DSO National Laboratories, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7189-8370","authenticated-orcid":false,"given":"Wen-Haw","family":"Chong","sequence":"additional","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 Design and Technology, 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":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Flamingo: a Visual Language Model for Few-Shot Learning. CoRR","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katie Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob Menick, Sebastian Borgeaud, Andrew Brock, Aida Nematzadeh, Sahand Sharifzadeh, Mikolaj Binkowski, Ricardo Barreira, Oriol Vinyals, Andrew Zisserman, and Karen Simonyan. 2022. Flamingo: a Visual Language Model for Few-Shot Learning. CoRR (2022). arXiv:2204.14198"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.156"},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT. 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.semeval-1.74"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.295"},{"key":"e_1_3_2_2_7_1","volume-title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 6325--6334","author":"Goyal Yash","year":"2017","unstructured":"Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, and Devi Parikh. 2017. Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 6325--6334."},{"key":"e_1_3_2_2_8_1","volume-title":"Decoding the Underlying Meaning of Multimodal Hateful Memes. arXiv preprint arXiv:2305.17678","author":"Hee Ming Shan","year":"2023","unstructured":"Ming Shan Hee, Wen-Haw Chong, and Roy Ka-Wei Lee. 2023. Decoding the Underlying Meaning of Multimodal Hateful Memes. arXiv preprint arXiv:2305.17678 (2023)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512260"},{"key":"e_1_3_2_2_10_1","volume-title":"GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 6700--6709","author":"Drew","unstructured":"Drew A. Hudson and Christopher D. Manning. 2019. GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 6700--6709."},{"key":"e_1_3_2_2_11_1","volume-title":"NeurIPS Workshop.","author":"Kiela Douwe","year":"2019","unstructured":"Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, and Davide Testuggine. 2019. Supervised Multimodal Bitransformers for Classifying Images and Text. In Visually Grounded Interaction and Language (ViGIL), NeurIPS Workshop."},{"key":"e_1_3_2_2_12_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_13_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_14_1","volume-title":"Disentangling Hate in Online Memes. In MM '21: ACM Multimedia Conference. 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. 5138--5147."},{"key":"e_1_3_2_2_15_1","volume-title":"Hoi","author":"Li Junnan","year":"2023","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. CoRR (2023). arXiv:2301.12597"},{"key":"e_1_3_2_2_16_1","volume-title":"BLIP: Bootstrap-ping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML","volume":"162","author":"Li Junnan","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven C. H. Hoi. 2022. BLIP: Bootstrap-ping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML, Vol. 162. 12888--12900."},{"key":"e_1_3_2_2_17_1","volume-title":"Shafiq R. Joty, Caiming Xiong, and Steven C. H. Hoi.","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Deepak Gotmare, Shafiq R. Joty, Caiming Xiong, and Steven C. H. Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. CoRR (2021). arXiv:2107.07651"},{"key":"e_1_3_2_2_18_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. CoRR","author":"Li Liunian Harold","year":"2019","unstructured":"Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. CoRR (2019). arXiv:1908.03557"},{"key":"e_1_3_2_2_19_1","volume-title":"Microsoft COCO: Common Objects in Context. In Computer Vision - ECCV European Conference","volume":"8693","author":"Lin Tsung-Yi","unstructured":"Tsung-Yi Lin, Michael Maire, Serge J. Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. In Computer Vision - ECCV European Conference, Vol. 8693. 740--755."},{"key":"e_1_3_2_2_20_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_21_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR (2019). arXiv:1907.11692"},{"key":"e_1_3_2_2_22_1","volume-title":"Fixing weight decay regularization in adam. CoRR","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Fixing weight decay regularization in adam. CoRR (2017). arXiv:1711.05101"},{"key":"e_1_3_2_2_23_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. CoRR","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. CoRR (2019). arXiv:1908.02265"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.woah-1.21"},{"key":"e_1_3_2_2_25_1","volume-title":"Bermano","author":"Mokady Ron","year":"2021","unstructured":"Ron Mokady, Amir Hertz, and Amit H. Bermano. 2021. ClipCap: CLIP Prefix for Image Captioning. CoRR (2021). arXiv:2111.09734"},{"key":"e_1_3_2_2_26_1","volume-title":"Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes. CoRR","author":"Muennighoff Niklas","year":"2020","unstructured":"Niklas Muennighoff. 2020. Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes. CoRR (2020). arXiv:2012.07788"},{"key":"e_1_3_2_2_27_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_28_1","volume-title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets. In Findings of the Association for Computational Linguistics: EMNLP. 4439--4455.","author":"Pramanick Shraman","year":"2021","unstructured":"Shraman Pramanick, Shivam Sharma, Dimitar Dimitrov, Md. Shad Akhtar, Preslav Nakov, and Tanmoy Chakraborty. 2021. MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets. In Findings of the Association for Computational Linguistics: EMNLP. 4439--4455."},{"key":"e_1_3_2_2_29_1","volume-title":"Proceedings of the International Conference on Machine Learning, ICML","volume":"139","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the International Conference on Machine Learning, ICML, Vol. 139. 8748--8763."},{"key":"e_1_3_2_2_30_1","volume-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"Ren Shaoqing","year":"2016","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2016. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE transactions on pattern analysis and machine intelligence 39, 6 (2016), 1137--1149."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_2_33_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. CoRR","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 (2023). arXiv:2302.13971"},{"key":"e_1_3_2_2_34_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_35_1","volume-title":"Multimodal Learning for Hateful Memes Detection. arXiv preprint arXiv:2011.12870","author":"Zhou Yi","year":"2020","unstructured":"Yi Zhou and Zhenhao Chen. 2020. Multimodal Learning for Hateful Memes Detection. arXiv preprint arXiv:2011.12870 (2020)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501247.3531557"},{"key":"e_1_3_2_2_37_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":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612498","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:40Z","timestamp":1755820840000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":37,"alternative-id":["10.1145\/3581783.3612498","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612498","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}