{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:08:10Z","timestamp":1784138890333,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809637","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"1255-1265","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Decoding Multimodal Cues: Unveiling the Implicit Meaning Behind Hateful Videos"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4094-2540","authenticated-orcid":false,"given":"Junyu","family":"Lu","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, Province \/ Municipality, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7561-9789","authenticated-orcid":false,"given":"Deyi","family":"Ji","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9590-6087","authenticated-orcid":false,"given":"Liqun","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9755-2471","authenticated-orcid":false,"given":"Xiaokun","family":"Zhang","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0565-2478","authenticated-orcid":false,"given":"Youlin","family":"Wu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"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\/0009-0007-1245-3604","authenticated-orcid":false,"given":"Peng","family":"Shu","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4676-2967","authenticated-orcid":false,"given":"Huan","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9658-5127","authenticated-orcid":false,"given":"Jie","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tencent, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4135-0683","authenticated-orcid":false,"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5557-7515","authenticated-orcid":false,"given":"Liang","family":"Yang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0872-7688","authenticated-orcid":false,"given":"Hongfei","family":"Lin","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"4309","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference, LREC 2020","author":"Alc\u00e2ntara Cleber","year":"2020","unstructured":"Cleber Alc\u00e2ntara, Viviane Pereira Moreira, and Diego de Vargas Feij\u00f3. 2020. Offensive Video Detection: Dataset and Baseline Results. In Proceedings of The 12th Language Resources and Evaluation Conference, LREC 2020, Marseille, France, May 11-16, 2020. European Language Resources Association, 4309-4319."},{"key":"e_1_3_2_1_2_1","volume-title":"MM-HSD: Multi-Modal Hate Speech Detection in Videos. arXiv preprint arXiv:2508.20546","author":"C\u00e9spedes-Sarrias Berta","year":"2025","unstructured":"Berta C\u00e9spedes-Sarrias, Carlos Collado-Capell, Pablo Rodenas-Ruiz, Olena Hrynenko, and Andrea Cavallaro. 2025. MM-HSD: Multi-Modal Hate Speech Detection in Videos. arXiv preprint arXiv:2508.20546 (2025)."},{"key":"e_1_3_2_1_3_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, Xuezhi Wang, Brennan Saeta, Mark Diaz, Orhan Firat, Michele Catasta, Jason Wei, Kathy Meier-Hellstern, Douglas Eck, Jeff Dean, Slav Petrov, and Noah Fiedel. 2023. PaLM: Scaling Language Modeling with Pathways. J. Mach. Learn. Res., Vol. 24 (2023), 240:1-240:113. http:\/\/jmlr.org\/papers\/v24\/22-1144.html","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.15402"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v17i1.22209"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019","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, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers), Jill Burstein, Christy Doran, and Thamar Solorio (Eds.). Association for Computational Linguistics, 4171-4186."},{"key":"e_1_3_2_1_7_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.29"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42001-024-00248-9"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/665"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 1-10","author":"Ji Deyi","year":"2025","unstructured":"Deyi Ji, Yuekui Yang, Liqun Liu, Peng Shu, Haiyang Wu, Shaogang Tang, Xudong Chen, Shaoping Ma, Tianrun Chen, and Lanyun Zhu. 2025b. RAVEN: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track. 1-10."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-industry.3"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.17682"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-demo.18"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"e_1_3_2_1_16_1","first-page":"2014","volume-title":"Image-based Content. In Companion Proceedings of the ACM on Web Conference 2025, WWW 2025","author":"Koushik Girish A.","year":"2025","unstructured":"Girish A. Koushik, Diptesh Kanojia, and Helen Treharne. 2025. Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image-based Content. In Companion Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025 - 2 May 2025. ACM, 2014-2023."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711680"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714560"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111457"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645381"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0424"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730014"},{"key":"e_1_3_2_1_23_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. CoRR Vol. abs\/2303.08774 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2303.08774 arXiv:2303.08774"},{"key":"e_1_3_2_1_24_1","volume-title":"Munich, Germany","volume":"658","author":"Owens Andrew","year":"2018","unstructured":"Andrew Owens and Alexei A. Efros. 2018. Audio-Visual Scene Analysis with Self-Supervised Multisensory Features. In Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part VI (Lecture Notes in Computer Science, Vol. 11210), Vittorio Ferrari, Martial Hebert, Cristian Sminchisescu, and Yair Weiss (Eds.). Springer, 639-658."},{"key":"e_1_3_2_1_25_1","volume-title":"Iterative Reasoning Preference Optimization. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024","author":"Pang Richard Yuanzhe","year":"2024","unstructured":"Richard Yuanzhe Pang, Weizhe Yuan, He He, Kyunghyun Cho, Sainbayar Sukhbaatar, and Jason Weston. 2024. Iterative Reasoning Preference Optimization. In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub M. Tomczak, and Cheng Zhang (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/d37c9ad425fe5b65304d500c6edcba00-Abstract-Conference.html"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.842"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.486"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2024.EMNLP-MAIN.54"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3566695"},{"key":"e_1_3_2_1_30_1","unstructured":"Romal Thoppilan Daniel De Freitas Jamie Hall Noam Shazeer Apoorv Kulshreshtha Heng-Tze Cheng Alicia Jin Taylor Bos Leslie Baker Yu Du YaGuang Li Hongrae Lee Huaixiu Steven Zheng Amin Ghafouri Marcelo Menegali Yanping Huang Maxim Krikun Dmitry Lepikhin James Qin Dehao Chen Yuanzhong Xu Zhifeng Chen Adam Roberts Maarten Bosma Yanqi Zhou Chung-Ching Chang Igor Krivokon Will Rusch Marc Pickett Kathleen S. Meier-Hellstern Meredith Ringel Morris Tulsee Doshi Renelito Delos Santos Toju Duke Johnny Soraker Ben Zevenbergen Vinodkumar Prabhakaran Mark Diaz Ben Hutchinson Kristen Olson Alejandra Molina Erin Hoffman-John Josh Lee Lora Aroyo Ravi Rajakumar Alena Butryna Matthew Lamm Viktoriya Kuzmina Joe Fenton Aaron Cohen Rachel Bernstein Ray Kurzweil Blaise Ag\u00fcera y Arcas Claire Cui Marian Croak Ed H. Chi and Quoc Le. 2022. LaMDA: Language Models for Dialog Applications. CoRR Vol. abs\/2201.08239 (2022). arXiv:2201.08239 https:\/\/arxiv.org\/abs\/2201.08239"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019","volume":"6569","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J. Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Multimodal Transformer for Unaligned Multimodal Language Sequences. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers. Association for Computational Linguistics, 6558-6569."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657664"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/694"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i46.41288"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3774904.3793046"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Hongbo Wang Junyu Lu Yan Han Kai Ma Liang Yang and Hongfei Lin. 2024b. Towards Patronizing and Condescending Language in Chinese Videos: A Multimodal Dataset and Detector. ICASSP 2025 - 2025 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) (2024) 1-5.","DOI":"10.1109\/ICASSP49660.2025.10890580"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714534"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681521"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3641960"},{"key":"e_1_3_2_1_40_1","volume-title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Wang Xuezhi","year":"2023","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023b. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/pdf?id=1PL1NIMMrw"},{"key":"e_1_3_2_1_41_1","volume-title":"HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2023","author":"Yang Yongjin","year":"2023","unstructured":"Yongjin Yang, Joonkee Kim, Yujin Kim, Namgyu Ho, James Thorne, and Se-Young Yun. 2023. HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2023, Singapore, December 6-10, 2023, Houda Bouamor, Juan Pino, and Kalika Bali (Eds.). Association for Computational Linguistics, 5490-5505."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/S11263-025-02613-1"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:31:26Z","timestamp":1784136686000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809637"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":42,"alternative-id":["10.1145\/3805712.3809637","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809637","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}