{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T04:42:10Z","timestamp":1776919330538,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":58,"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\/3581783.3611761","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"4788-4797","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Invariant Meets Specific: A Scalable Harmful Memes Detection Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0601-2224","authenticated-orcid":false,"given":"Chuanpeng","family":"Yang","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, School of Cyber Security, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7061-3329","authenticated-orcid":false,"given":"Fuqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, School of Cyber Security, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1107-3873","authenticated-orcid":false,"given":"Jizhong","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7170-3809","authenticated-orcid":false,"given":"Songlin","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences & University of Chinese Academy of Sciences, School of Cyber Security, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5393"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157135"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1239"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.707"},{"key":"e_1_3_2_1_7_1","volume-title":"Japsimar Singh Wahi, and Siyao Li","author":"Das Abhishek","year":"2020","unstructured":"Abhishek Das, Japsimar Singh Wahi, and Siyao Li. 2020. Detecting hate speech in multi-modal memes. arXiv preprint arXiv:2012.14891 (2020)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","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, Volume 1 (Long and Short Papers). 4171--4186."},{"key":"e_1_3_2_1_9_1","volume-title":"Game-on: Graph attention network based multimodal fusion for fake news detection. arXiv preprint arXiv:2202.12478","author":"Dhawan Mudit","year":"2022","unstructured":"Mudit Dhawan, Shakshi Sharma, Aditya Kadam, Rajesh Sharma, and Ponnurangam Kumaraguru. 2022. Game-on: Graph attention network based multimodal fusion for fake news detection. arXiv preprint arXiv:2202.12478 (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_11_1","volume-title":"Mario Marchand, and Victor Lempitsky.","author":"Ganin Yaroslav","year":"2016","unstructured":"Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Francc ois Laviolette, Mario Marchand, and Victor Lempitsky. 2016. Domain-adversarial training of neural networks. The journal of machine learning research (2016), 2096--2030."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR","author":"Hoffman Judy","year":"2018","unstructured":"Judy Hoffman, Eric Tzeng, Taesung Park, Jun-Yan Zhu, Phillip Isola, Kate Saenko, Alexei Efros, and Trevor Darrell. 2018. Cycada: Cycle-consistent adversarial domain adaptation. In International conference on machine learning. PMLR, 1989--1998."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16533"},{"key":"e_1_3_2_1_15_1","volume-title":"Supervised Multimodal Bitransformers for Classifying Images and Text. arXiv preprint arXiv:1909.02950","author":"Kiela Douwe","year":"2019","unstructured":"Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, and Davide Testuggine. 2019. Supervised Multimodal Bitransformers for Classifying Images and Text. arXiv preprint arXiv:1909.02950 (2019)."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems. 2611--2624","author":"Kiela Douwe","year":"2020","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 Proceedings of the 34th International Conference on Neural Information Processing Systems. 2611--2624."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475625"},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Machine Learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems. 9694--9705","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath R Selvaraju, Akhilesh Deepak Gotmare, Shafiq Joty, Caiming Xiong, and Steven Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. In Proceedings of Advances in Neural Information Processing Systems. 9694--9705."},{"key":"e_1_3_2_1_20_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557","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. arXiv preprint arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475190"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.124"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.786"},{"key":"e_1_3_2_1_24_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_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1001"},{"key":"e_1_3_2_1_26_1","volume-title":"International conference on machine learning. 97--105","author":"Long Mingsheng","year":"2015","unstructured":"Mingsheng Long, Yue Cao, Jianmin Wang, and Michael Jordan. 2015. Learning transferable features with deep adaptation networks. In International conference on machine learning. 97--105."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems. 1647--1657","author":"Long Mingsheng","year":"2018","unstructured":"Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael I Jordan. 2018. Conditional adversarial domain adaptation. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. 1647--1657."},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on machine learning. PMLR, 2208--2217","author":"Long Mingsheng","year":"2017","unstructured":"Mingsheng Long, Han Zhu, Jianmin Wang, and Michael I Jordan. 2017. Deep transfer learning with joint adaptation networks. In International conference on machine learning. PMLR, 2208--2217."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems. 13--23","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. In Proceedings of the 33rd International Conference on Neural Information Processing Systems. 13--23."},{"key":"e_1_3_2_1_30_1","volume-title":"International conference on machine learning. PMLR, 3--13","author":"Maas Andrew L","year":"2013","unstructured":"Andrew L Maas, Awni Y Hannun, Andrew Y Ng, et al. 2013. Rectifier nonlinearities improve neural network acoustic models. In International conference on machine learning. PMLR, 3--13."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.124"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"e_1_3_2_1_34_1","volume-title":"Preslav Nakov, and Tanmoy Chakraborty.","author":"Pramanick Shraman","year":"2021","unstructured":"Shraman Pramanick, Shivam Sharma, Dimitar Dimitrov, Md Shad Akhtar, Preslav Nakov, and Tanmoy Chakraborty. 2021b. MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets. In Findings of the Association for Computational Linguistics: EMNLP 2021. 4439--4455."},{"key":"e_1_3_2_1_35_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning. 8748--8763","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, et al. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning. 8748--8763."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1096"},{"key":"e_1_3_2_1_37_1","volume-title":"Detecting hateful memes using a multimodal deep ensemble. arXiv preprint arXiv:2012.13235","author":"Sandulescu Vlad","year":"2020","unstructured":"Vlad Sandulescu. 2020. Detecting hateful memes using a multimodal deep ensemble. arXiv preprint arXiv:2012.13235 (2020)."},{"key":"e_1_3_2_1_38_1","volume-title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In International Conference on Learning Representations.","author":"Su Weijie","year":"2020","unstructured":"Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai. 2020. VL-BERT: Pre-training of Generic Visual-Linguistic Representations. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the second workshop on trolling, aggression and cyberbullying. 32--41","author":"Suryawanshi Shardul","year":"2020","unstructured":"Shardul Suryawanshi, Bharathi Raja Chakravarthi, Mihael Arcan, and Paul Buitelaar. 2020. Multimodal meme dataset (MultiOFF) for identifying offensive content in image and text. In Proceedings of the second workshop on trolling, aggression and cyberbullying. 32--41."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/189"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22","author":"Tian Yijun","unstructured":"Yijun Tian, Chuxu Zhang, Zhichun Guo, Chao Huang, Ronald Metoyer, and Nitesh V. Chawla. 2022b. RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22. 3466--3472."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.00038"},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of Advances in Neural Information Processing systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of Advances in Neural Information Processing systems, Vol. 30."},{"key":"e_1_3_2_1_44_1","volume-title":"Graph Attention Networks. In International Conference on Learning Representations.","author":"Petar Velivc","year":"2018","unstructured":"Petar Velivc kovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph Attention Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_45_1","volume-title":"Detecting hate speech in memes using multimodal deep learning approaches: Prize-winning solution to hateful memes challenge. arXiv preprint arXiv:2012.12975","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. arXiv preprint arXiv:2012.12975 (2020)."},{"key":"e_1_3_2_1_46_1","volume-title":"Learning dual semantic relations with graph attention for image-text matching","author":"Wen Keyu","year":"2020","unstructured":"Keyu Wen, Xiaodong Gu, and Qingrong Cheng. 2020. Learning dual semantic relations with graph attention for image-text matching. IEEE transactions on circuits and systems for video technology, Vol. 31, 7 (2020), 2866--2879."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.349"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548255"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"e_1_3_2_1_51_1","volume-title":"Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning. In International Conference on Learning Representations.","author":"Zellinger Werner","year":"2017","unstructured":"Werner Zellinger, Thomas Grubinger, Edwin Lughofer, Thomas Natschl\u00e4ger, and Susanne Saminger-Platz. 2017. Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17687"},{"key":"e_1_3_2_1_53_1","volume-title":"TOT: Topology-Aware Optimal Transport For Multimodal Hate Detection. arXiv preprint arXiv:2303.09314","author":"Zhang Linhao","year":"2023","unstructured":"Linhao Zhang, Li Jin, Xian Sun, Guangluan Xu, Zequn Zhang, Xiaoyu Li, Nayu Liu, Shiyao Yan, and Qing Liu. 2023. TOT: Topology-Aware Optimal Transport For Multimodal Hate Detection. arXiv preprint arXiv:2303.09314 (2023)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/333"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455994"},{"key":"e_1_3_2_1_56_1","volume-title":"Enhance multimodal transformer with external label and in-domain pretrain: Hateful meme challenge winning solution. arXiv preprint arXiv:2012.08290","author":"Zhu Ron","year":"2020","unstructured":"Ron Zhu. 2020. Enhance multimodal transformer with external label and in-domain pretrain: Hateful meme challenge winning solution. arXiv preprint arXiv:2012.08290 (2020)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475648"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015989"}],"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\/3581783.3611761","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:13:50Z","timestamp":1755821630000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611761"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":58,"alternative-id":["10.1145\/3581783.3611761","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611761","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"}}]}}