{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:10:39Z","timestamp":1765343439085,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758279","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"13228-13234","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CH-SV: A Benchmark for Multi-Type Chinese Harmful Short Video Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1116-1016","authenticated-orcid":false,"given":"Linlin","family":"Zong","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6355-0697","authenticated-orcid":false,"given":"Shilin","family":"Sui","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1478-5503","authenticated-orcid":false,"given":"Wenjun","family":"Liang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3542-227X","authenticated-orcid":false,"given":"Wanyu","family":"Song","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9504-1718","authenticated-orcid":false,"given":"Linlin","family":"Tian","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9036-4665","authenticated-orcid":false,"given":"Xinyue","family":"Liu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0180-3740","authenticated-orcid":false,"given":"Xianchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5453-978X","authenticated-orcid":false,"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection. arXiv preprint arXiv:2501.15451","author":"Bai Zewen","year":"2025","unstructured":"Zewen Bai, Yuanyuan Sun, Shengdi Yin, Junyu Lu, Jingjie Zeng, Haohao Zhu, Liang Yang, and Hongfei Lin. 2025. STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection. arXiv preprint arXiv:2501.15451 (2025)."},{"key":"e_1_3_2_1_2_1","volume-title":"Resolving Unseen Rumors with Retrieval-Augmented Large Language Models. In CCF International Conference on Natural Language Processing and Chinese Computing. Springer, 319-332","author":"Chen Lei","year":"2024","unstructured":"Lei Chen and Zhongyu Wei. 2024. Resolving Unseen Rumors with Retrieval-Augmented Large Language Models. In CCF International Conference on Natural Language Processing and Chinese Computing. Springer, 319-332."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511968"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482212"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v14i1.7350"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.796"},{"key":"e_1_3_2_1_7_1","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","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_8_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 14815-14824","author":"Gan Tian","year":"2023","unstructured":"Tian Gan, Qing Wang, Xingning Dong, Xiangyuan Ren, Liqiang Nie, and Qingpei Guo. 2023. Cnvid-3.5 m: Build, filter, and pre-train the large-scale public chinese video-text dataset. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 14815-14824."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583870"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093414"},{"key":"e_1_3_2_1_11_1","first-page":"131","article-title":"CNN architectures for large-scale audio classification. In 2017 ieee international conference on acoustics, speech and signal processing (icassp)","author":"Hershey Shawn","year":"2017","unstructured":"Shawn Hershey, Sourish Chaudhuri, Daniel PW Ellis, Jort F Gemmeke, Aren Jansen, R Channing Moore, Manoj Plakal, Devin Platt, Rif A Saurous, Bryan Seybold, et al., 2017. CNN architectures for large-scale audio classification. In 2017 ieee international conference on acoustics, speech and signal processing (icassp). IEEE, 131-135.","journal-title":"IEEE"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.osnem.2021.100182"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.611"},{"key":"e_1_3_2_1_14_1","first-page":"15566","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING","author":"Lu Junyu","year":"2024","unstructured":"Junyu Lu, Bo Xu, Xiaokun Zhang, Kaiyuan Liu, Dongyu Zhang, Liang Yang, and Hongfei Lin. 2024a. Take Its Essence, Discard Its Dross! Debiasing for Toxic Language Detection via Counterfactual Causal Effect. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 15566-15578."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.898"},{"key":"e_1_3_2_1_16_1","first-page":"13302","article-title":"Towards comprehensive detection of chinese harmful memes","volume":"37","author":"Lu Junyu","year":"2024","unstructured":"Junyu Lu, Bo Xu, Xiaokun Zhang, Hongbo Wang, Haohao Zhu, Dongyu Zhang, Liang Yang, and Hongfei Lin. 2024b. Towards comprehensive detection of chinese harmful memes. Advances in Neural Information Processing Systems, Vol. 37 (2024), 13302-13320.","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Blockchain applications for healthcare informatics","author":"Mohbey Krishna Kumar","key":"e_1_3_2_1_17_1","unstructured":"Krishna Kumar Mohbey, Savita Sharma, Sunil Kumar, and Meenu Sharma. 2022. COVID-19 identification and analysis using CT scan images: Deep transfer learning-based approach. In Blockchain applications for healthcare informatics. Elsevier, 447-470."},{"key":"e_1_3_2_1_18_1","volume-title":"Emotion recognition from speech using wav2vec 2.0 embeddings. arXiv preprint arXiv:2104.03502","author":"Pepino Leonardo","year":"2021","unstructured":"Leonardo Pepino, Pablo Riera, and Luciana Ferrer. 2021. Emotion recognition from speech using wav2vec 2.0 embeddings. arXiv preprint arXiv:2104.03502 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26689"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.157"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the WILDRE5-5th workshop on indian language data: resources and evaluation. 7-13","author":"Suryawanshi Shardul","year":"2020","unstructured":"Shardul Suryawanshi, Bharathi Raja Chakravarthi, Pranav Verma, Mihael Arcan, John Philip McCrae, and Paul Buitelaar. 2020. A dataset for troll classification of TamilMemes. In Proceedings of the WILDRE5-5th workshop on indian language data: resources and evaluation. 7-13."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the NAACL student research workshop. 88-93","author":"Talat Zeerak","year":"2016","unstructured":"Zeerak Talat and Dirk Hovy. 2016. Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In Proceedings of the NAACL student research workshop. 88-93."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the conference. Association for computational linguistics. Meeting","volume":"2019","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 conference. Association for computational linguistics. Meeting, Vol. 2019. 6558."},{"key":"e_1_3_2_1_26_1","volume-title":"News Consumption Across Social Media in. Pew Research Centers","author":"Walker Mason","year":"2021","unstructured":"Mason Walker and Katerina Eva Matsa. 2021. News Consumption Across Social Media in. Pew Research Centers (2021)."},{"key":"e_1_3_2_1_27_1","volume-title":"Usman Naseem, and Roy Ka-Wei Lee. [n.d.]. MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili. In ACM Multimedia","author":"Wang Han","year":"2024","unstructured":"Han Wang, Rui Yang Tan, Usman Naseem, and Roy Ka-Wei Lee. [n.d.]. MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili. In ACM Multimedia 2024."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2067"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548098"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479931"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:08:43Z","timestamp":1765343323000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758279"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":30,"alternative-id":["10.1145\/3746027.3758279","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758279","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}