{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T16:52:06Z","timestamp":1781542326452,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"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":[[2026,6,16]]},"DOI":"10.1145\/3805622.3810724","type":"proceedings-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T14:42:57Z","timestamp":1781534577000},"page":"2646-2655","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HCG-MPB: Hierarchical Complementary Gating Mechanism with Multimodal Pattern Bank for Hateful Video Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0562-6835","authenticated-orcid":false,"given":"Hongxia","family":"Sun","sequence":"first","affiliation":[{"name":"Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9351-8738","authenticated-orcid":false,"given":"Wenzhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7704-5045","authenticated-orcid":false,"given":"Yabo","family":"Yin","sequence":"additional","affiliation":[{"name":"Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9660-3157","authenticated-orcid":false,"given":"Fuyuan","family":"Wei","sequence":"additional","affiliation":[{"name":"Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0297-4995","authenticated-orcid":false,"given":"Junhang","family":"Wu","sequence":"additional","affiliation":[{"name":"Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3365-6409","authenticated-orcid":false,"given":"Junjiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.622"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Rana Al-Maroof Kevin Ayoubi Khadija Alhumaid Ahmad Aburayya Muhammad Alshurideh Raghad Alfaisal and Said Salloum. 2021. The acceptance of social media video for knowledge acquisition sharing and application: A comparative study among YouYube users and TikTok users\u2019 for medical purposes. International Journal of Data and Network Science 5 3 (2021) 197.","DOI":"10.5267\/j.ijdns.2021.6.013"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA47632.2019.9035228"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612498"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.22"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3648145"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.woah-1.3"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3672041"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v17i1.22209"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Steven Davis and Paul Mermelstein. 1980. Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE transactions on acoustics speech and signal processing 28 4 (1980) 357\u2013366.","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"e_1_3_3_1_14_2","first-page":"4171","volume-title":"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)","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\u20134186."},{"key":"e_1_3_3_1_15_2","unstructured":"Alexey Dosovitskiy. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.11929 (2020)."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Ankita Gandhi Param Ahir Kinjal Adhvaryu Pooja Shah Ritika Lohiya Erik Cambria Soujanya Poria and Amir Hussain. 2024. Hate speech detection: A comprehensive review of recent works. Expert Systems 41 8 (2024) e13562.","DOI":"10.1111\/exsy.13562"},{"key":"e_1_3_3_1_17_2","unstructured":"Xudong Han Junjie Yang Tianyang Wang Ziqian Bi Junfeng Hao and Jun-Jie Song. 2025. Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models. ArXiv abs\/2508.17184 (2025). https:\/\/api.semanticscholar.org\/CorpusID:280710355"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3641249"},{"key":"e_1_3_3_1_19_2","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. Advances in neural information processing systems 33 (2020) 2611\u20132624."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Dirk Kindermann. 2023. Against \u2018hate speech\u2019. Journal of Applied Philosophy 40 5 (2023) 813\u2013835.","DOI":"10.1111\/japp.12648"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3718382"},{"key":"e_1_3_3_1_22_2","unstructured":"Gokul\u00a0Karthik Kumar and Karthik Nandakumar. 2022. Hate-clipper: Multimodal hateful meme classification based on cross-modal interaction of clip features. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.05916 (2022)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714560"},{"key":"e_1_3_3_1_24_2","unstructured":"Bo Li Yuanhan Zhang Dong Guo Renrui Zhang Feng Li Hao Zhang Kaichen Zhang Peiyuan Zhang Yanwei Li Ziwei Liu et\u00a0al. 2024. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.03326 (2024)."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Hongzhan Lin Ziyang Luo Wei Gao Jing Ma Bo Wang and Ruichao Yang. 2024. Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models. Proceedings of the ACM Web Conference 2024 (2024) 2359\u20132370.","DOI":"10.1145\/3589334.3645381"},{"key":"e_1_3_3_1_26_2","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1907.11692 (2019)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Zhiyu Ma Shaowen Yao Liwen Wu Song Gao and Yunqi Zhang. 2022. Hateful memes detection based on multi-task learning. Mathematics 10 23 (2022) 4525.","DOI":"10.3390\/math10234525"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Krishanu Maity AS Poornash Sriparna Saha and Pushpak Bhattacharyya. 2024. Toxvidlm: A multimodal framework for toxicity detection in code-mixed videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.20628 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.663"},{"key":"e_1_3_3_1_29_2","unstructured":"Elyas Meguellati Assaad Zeghina Shazia Sadiq and Gianluca Demartini. 2025. LLM-based Semantic Augmentation for Harmful Content Detection. arxiv:https:\/\/arXiv.org\/abs\/2504.15548\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2504.15548"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.291"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Marzieh Mozafari Reza Farahbakhsh and No\u00ebl Crespi. 2020. Hate speech detection and racial bias mitigation in social media based on BERT model. PloS one 15 8 (2020) e0237861.","DOI":"10.1371\/journal.pone.0237861"},{"key":"e_1_3_3_1_32_2","unstructured":"Fengjun Pan Anh\u00a0Tuan Luu and Xiaobao Wu. 2025. Detecting Harmful Memes with Decoupled Understanding and Guided CoT Reasoning. (2025)."},{"key":"e_1_3_3_1_33_2","first-page":"28492","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International conference on machine learning. PMLR, 28492\u201328518."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.842"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"Pradeep\u00a0Kumar Roy Asis\u00a0Kumar Tripathy Tapan\u00a0Kumar Das and Xiao-Zhi Gao. 2020. A framework for hate speech detection using deep convolutional neural network. IEEE Access 8 (2020) 204951\u2013204962.","DOI":"10.1109\/ACCESS.2020.3037073"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"George-Alexandru Vlad George-Eduard Zaharia Dumitru-Clementin Cercel and Mihai Dascalu. 2020. UPB@ DANKMEMES: Italian memes analysis-employing visual models and graph convolutional networks for meme identification and hate speech detection. EVALITA evaluation of NLP and speech tools for Italian 288 (2020).","DOI":"10.4000\/books.aaccademia.7360"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681521"},{"key":"e_1_3_3_1_38_2","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et\u00a0al. 2024. Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.12191 (2024)."},{"key":"e_1_3_3_1_39_2","unstructured":"Yu Xia Rui Wang Xu Liu Mingyan Li Tong Yu Xiang Chen Julian Mcauley and Shuai Li. 2024. Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs. (2024)."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Haitao Xiong Wei Jiao and Yuanyuan Cai. 2025. TCE-DBF: textual context enhanced dynamic bimodal fusion for hate video detection. Data Technologies and Applications 59 2 (2025) 201\u2013215.","DOI":"10.1108\/DTA-02-2024-0211"},{"key":"e_1_3_3_1_41_2","first-page":"12","volume-title":"Proceedings of the 2019 9th International Conference on Information and Social Science (ICISS 2019), Manila, Philippines","author":"Yang Shuai","year":"2019","unstructured":"Shuai Yang, Yuzhen Zhao, and Yifang Ma. 2019. Analysis of the reasons and development of short video application-Taking Tik Tok as an example. In Proceedings of the 2019 9th International Conference on Information and Social Science (ICISS 2019), Manila, Philippines. 12\u201314."},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"crossref","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.00321 (2023).","DOI":"10.18653\/v1\/2023.findings-emnlp.365"},{"key":"e_1_3_3_1_43_2","unstructured":"Yuan Yao Tianyu Yu Ao Zhang Chongyi Wang Junbo Cui Hongji Zhu Tianchi Cai Haoyu Li Weilin Zhao Zhihui He et\u00a0al. 2024. Minicpm-v: A gpt-4v level mllm on your phone. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.01800 (2024)."},{"key":"e_1_3_3_1_44_2","unstructured":"Jiangbei Yue Shuonan Yang Tailin Chen Jianbo Jiao and Zeyu Fu. 2025. Multimodal Hate Detection Using Dual-Stream Graph Neural Networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.13515 (2025)."},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW65004.2024.00030"},{"key":"e_1_3_3_1_46_2","unstructured":"Wayne\u00a0Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et\u00a0al. 2023. A survey of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.18223 1 2 (2023)."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Fan Zhou Xovee Xu Goce Trajcevski and Kunpeng Zhang. 2021. A Survey of Information Cascade Analysis: Models Predictions and Recent Advances. Comput. Surveys 54 2 (2021) 27:1\u201327:36.","DOI":"10.1145\/3433000"}],"event":{"name":"ICMR '26: International Conference on Multimedia Retrieval","location":"Amsterdam The Netherlands","acronym":"ICMR '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 International Conference on Multimedia Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:54:21Z","timestamp":1781538861000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805622.3810724"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":46,"alternative-id":["10.1145\/3805622.3810724","10.1145\/3805622"],"URL":"https:\/\/doi.org\/10.1145\/3805622.3810724","relation":{},"subject":[],"published":{"date-parts":[[2026,6,15]]},"assertion":[{"value":"2026-06-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}