{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:17:00Z","timestamp":1776889020423,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","funder":[{"name":"Alan Turing Institute","award":["SDCfP2\\100016"],"award-info":[{"award-number":["SDCfP2\\100016"]}]},{"name":"DSO National Laboratories - Singapore","award":["SDCfP2\\100016"],"award-info":[{"award-number":["SDCfP2\\100016"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3728481.3762164","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:53:41Z","timestamp":1761404021000},"page":"26-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Revealing Temporal Label Noise in Multimodal Hateful Video Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6883-3540","authenticated-orcid":false,"given":"Shuonan","family":"Yang","sequence":"first","affiliation":[{"name":"Multimodal Intelligence Lab, Department of Computer Science, University of Exeter, Exeter, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1762-4245","authenticated-orcid":false,"given":"Tailin","family":"Chen","sequence":"additional","affiliation":[{"name":"Multimodal Intelligence Lab, Department of Computer Science, University of Exeter, Exeter, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3450-0204","authenticated-orcid":false,"given":"Rahul","family":"Singh","sequence":"additional","affiliation":[{"name":"Multimodal Intelligence Lab, Department of Computer Science, University of Exeter, Exeter, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4851-4321","authenticated-orcid":false,"given":"Jiangbei","family":"Yue","sequence":"additional","affiliation":[{"name":"Multimodal Intelligence Lab, Department of Computer Science, University of Exeter, Exeter, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0833-5115","authenticated-orcid":false,"given":"Jianbo","family":"Jiao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Birmingham, Birmingham, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2076-7597","authenticated-orcid":false,"given":"Zeyu","family":"Fu","sequence":"additional","affiliation":[{"name":"Multimodal Intelligence Lab, Department of Computer Science, University of Exeter, Exeter, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/2981345.2981354"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/SocialCom-PASSAT.2012.55"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377323"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v17i1.22209"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_2_1_7_1","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. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_8_1","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. arXiv:2010.11929 [cs.CV] https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858535"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3013"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3587427"},{"key":"e_1_3_2_1_12_1","unstructured":"Glenn Jocher Ayush Chaurasia and Jing Qiu. 2023. Ultralytics YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Christos Koutlis Manos Schinas and Symeon Papadopoulos. 2023. MemeFier: Dual-stage Modality Fusion for Image Meme Classification. arXiv:2304.02906 [cs.CV] https:\/\/arxiv.org\/abs\/2304.02906","DOI":"10.1145\/3591106.3592254"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714560"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126479"},{"key":"e_1_3_2_1_16_1","volume-title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv:1802.03426 [stat.ML] https:\/\/arxiv.org\/abs\/1802.03426","author":"McInnes Leland","year":"2020","unstructured":"Leland McInnes, John Healy, and James Melville. 2020. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv:1802.03426 [stat.ML] https:\/\/arxiv.org\/abs\/1802.03426"},{"key":"e_1_3_2_1_17_1","volume-title":"Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. arXiv preprint arXiv:1003.4083","author":"Muda Lindasalwa","year":"2010","unstructured":"Lindasalwa Muda, Mumtaj Begam, and Irraivan Elamvazuthi. 2010. Voice recognition algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques. arXiv preprint arXiv:1003.4083 (2010)."},{"key":"e_1_3_2_1_18_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. 2021. MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets. arXiv:2109.05184 [cs.MM] https:\/\/arxiv.org\/abs\/2109.05184"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2976248.2976426"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714534"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681521"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW65004.2024.00030"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"Zimmerman Steven","year":"2018","unstructured":"Steven Zimmerman, Udo Kruschwitz, and Chris Fox. 2018. Improving Hate Speech Detection with Deep Learning Ensembles. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Nicoletta Calzolari, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Koiti Hasida, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, H\u00e9l\u00e8ne Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis, and Takenobu Tokunaga (Eds.). European Language Resources Association (ELRA), Miyazaki, Japan. https:\/\/aclanthology.org\/L18-1404\/"}],"event":{"name":"MM '25:The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 4th International Workshop on Multimodal Human Understanding for the Web and Social Media"],"original-title":[],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T14:53:43Z","timestamp":1761404023000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3728481.3762164"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":23,"alternative-id":["10.1145\/3728481.3762164","10.1145\/3728481"],"URL":"https:\/\/doi.org\/10.1145\/3728481.3762164","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]},"assertion":[{"value":"2025-10-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}