{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T02:38:45Z","timestamp":1783564725347,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","funder":[{"name":"Australian Commonwealth Scientific and Industrial Research Organization (CSIRO) in coniunction with the National Science Foundation (NSF)","award":["CSIRO-NSF\\#2303037"],"award-info":[{"award-number":["CSIRO-NSF\\#2303037"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792362","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:34Z","timestamp":1775771674000},"page":"7178-7188","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["TrueLens: Video Fake News Detection with Dual Level Evidence Gathering and Consolidation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0390-0747","authenticated-orcid":false,"given":"Junyi","family":"Chen","sequence":"first","affiliation":[{"name":"University of Auckland, Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3162-935X","authenticated-orcid":false,"given":"Qian","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Auckland, Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1979-6622","authenticated-orcid":false,"given":"Jing","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Auckland, Auckland, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7731-0301","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Technology, Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4004-z"},{"key":"e_1_3_2_1_2_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_3_1","first-page":"9690","article-title":"Towards causal vqa: Revealing and reducing spurious correlations by invariant and covariant semantic editing","author":"Agarwal Vedika","year":"2020","unstructured":"Vedika Agarwal, Rakshith Shetty, and Mario Fritz. 2020. Towards causal vqa: Revealing and reducing spurious correlations by invariant and covariant semantic editing. In CVPR. 9690-9698.","journal-title":"CVPR."},{"key":"e_1_3_2_1_4_1","first-page":"4971","article-title":"Don't just assume; look and answer: Overcoming priors for visual question answering","author":"Agrawal Aishwarya","year":"2018","unstructured":"Aishwarya Agrawal, Dhruv Batra, Devi Parikh, and Aniruddha Kembhavi. 2018. Don't just assume; look and answer: Overcoming priors for visual question answering. In CVPR. 4971-4980.","journal-title":"CVPR."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680663"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583259"},{"key":"e_1_3_2_1_7_1","volume-title":"A Closer Look at Multimodal Representation Collapse. arXiv:2505.22483","author":"Chaudhuri Abhra","year":"2025","unstructured":"Abhra Chaudhuri, Anjan Dutta, Tu Bui, and Serban Georgescu. 2025. A Closer Look at Multimodal Representation Collapse. arXiv:2505.22483 (2025)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511968"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482212"},{"key":"e_1_3_2_1_10_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_11_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:2010.11929 (2020)."},{"key":"e_1_3_2_1_12_1","volume-title":"NeurIPS","volume":"17","author":"Grandvalet Yves","year":"2004","unstructured":"Yves Grandvalet and Yoshua Bengio. 2004. Semi-supervised learning by entropy minimization. NeurIPS, Vol. 17 (2004)."},{"key":"e_1_3_2_1_13_1","unstructured":"Dan Hendrycks and Kevin Gimpel. 2017. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. In ICLR."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714559"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3353763"},{"key":"e_1_3_2_1_16_1","volume-title":"MAGE-fend: Multimodal Adaptive Fusion with Guidance from LLM Expertise for Fake News Detection on Short Video Platforms. Knowledge-Based Systems","author":"Hu Lingtong","year":"2025","unstructured":"Lingtong Hu, Zituo Wang, Jiayi Zhu, Yifan Hu, and Xianbing Wang. 2025. MAGE-fend: Multimodal Adaptive Fusion with Guidance from LLM Expertise for Fake News Detection on Short Video Platforms. Knowledge-Based Systems (2025), 114298."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651509"},{"key":"e_1_3_2_1_18_1","volume-title":"Map: Multimodal uncertainty-aware vision-language pre-training model. In CVPR.","author":"Ji Yatai","year":"2023","unstructured":"Yatai Ji, Junjie Wang, Yuan Gong, Lin Zhang, Yanru Zhu, Hongfa Wang, Jiaxing Zhang, Tetsuya Sakai, and Yujiu Yang. 2023. Map: Multimodal uncertainty-aware vision-language pre-training model. In CVPR."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218488501000831"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-42337-1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75256-1_36"},{"key":"e_1_3_2_1_22_1","volume-title":"NeurIPS","volume":"30","author":"Lakshminarayanan Balaji","year":"2017","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. NeurIPS, Vol. 30 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"Llava-onevision: Easy visual task transfer. arXiv:2408.03326","author":"Li Bo","year":"2024","unstructured":"Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, et al., 2024b. Llava-onevision: Easy visual task transfer. arXiv:2408.03326 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645385"},{"key":"e_1_3_2_1_25_1","unstructured":"Yili Li Jian Lang Rongpei Hong Qing Chen Zhangtao Cheng Jia Chen Ting Zhong and Fan Zhou. [n.d.]. REAL: Retrieval-Augmented Prototype Alignment for Improved Fake News Video Detection. ([n.d.])."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v17i1.22168"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103426"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627508.3638341"},{"key":"e_1_3_2_1_29_1","unstructured":"Kai Wang Ng Guo-Liang Tian and Man-Lai Tang. 2011. Dirichlet and related distributions: Theory methods and applications. (2011)."},{"key":"e_1_3_2_1_30_1","volume-title":"NeurIPS","volume":"32","author":"Ovadia Yaniv","year":"2019","unstructured":"Yaniv Ovadia, Emily Fertig, Jie Ren, Zachary Nado, David Sculley, Sebastian Nowozin, Joshua Dillon, Balaji Lakshminarayanan, and Jasper Snoek. 2019. Can you trust your model's uncertainty? evaluating predictive uncertainty under dataset shift. NeurIPS, Vol. 32 (2019)."},{"key":"e_1_3_2_1_31_1","volume-title":"A corpus of debunked and verified user-generated videos. Online information review","author":"Papadopoulou Olga","year":"2019","unstructured":"Olga Papadopoulou, Markos Zampoglou, Symeon Papadopoulos, and Ioannis Kompatsiaris. 2019. A corpus of debunked and verified user-generated videos. Online information review, Vol. 43, 1 (2019), 72-88."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078897.3080535"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26689"},{"key":"e_1_3_2_1_34_1","volume-title":"Two heads are better than one: Improving fake news video detection by correlating with neighbors. arXiv:2306.05241","author":"Qi Peng","year":"2023","unstructured":"Peng Qi, Yuyang Zhao, Yufeng Shen, Wei Ji, Juan Cao, and Tat-Seng Chua. 2023b. Two heads are better than one: Improving fake news video detection by correlating with neighbors. arXiv:2306.05241 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462871"},{"key":"e_1_3_2_1_36_1","volume-title":"Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever.","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In ICML."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.20"},{"key":"e_1_3_2_1_38_1","volume-title":"wav2vec: Unsupervised pre-training for speech recognition. arXiv:1904.05862","author":"Schneider Steffen","year":"2019","unstructured":"Steffen Schneider, Alexei Baevski, Ronan Collobert, and Michael Auli. 2019. wav2vec: Unsupervised pre-training for speech recognition. arXiv:1904.05862 (2019)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671928"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.214"},{"key":"e_1_3_2_1_41_1","first-page":"725","volume-title":"Explainable Manipulated Videos Detection Using Multimodal Large Language Models. In Companion Proceedings of the ACM on Web Conference","author":"Tran Khoa-Dang","year":"2025","unstructured":"Khoa-Dang Tran. 2025. Explainable Manipulated Videos Detection Using Multimodal Large Language Models. In Companion Proceedings of the ACM on Web Conference 2025. 725-728."},{"key":"e_1_3_2_1_42_1","volume-title":"Consistency-Aware Fake Videos Detection on Short Video Platforms. In International Conference on Intelligent Computing. Springer, 200-210","author":"Wang Junxi","year":"2025","unstructured":"Junxi Wang, Jize Liu, Na Zhang, and Yaxiong Wang. 2025a. Consistency-Aware Fake Videos Detection on Short Video Platforms. In International Conference on Intelligent Computing. Springer, 200-210."},{"key":"e_1_3_2_1_43_1","volume-title":"FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapter. arXiv:2508.19639","author":"Wang Junxi","year":"2025","unstructured":"Junxi Wang, Yaxiong Wang, Lechao Cheng, and Zhun Zhong. 2025b. FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapter. arXiv:2508.19639 (2025)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657905"},{"key":"e_1_3_2_1_45_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3204444"},{"key":"e_1_3_2_1_47_1","volume-title":"WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization. In The Thirty-ninth Annual Conference on Neural Information Processing Systems.","author":"Wen Jiahao","unstructured":"Jiahao Wen, Hang Yu, and Zhedong Zheng. [n.d.]. WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization. In The Thirty-ninth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-019-01617-y"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645468"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714498"},{"key":"e_1_3_2_1_51_1","volume-title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese. arXiv:2211.01335","author":"Yang An","year":"2022","unstructured":"An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, and Chang Zhou. 2022. Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese. arXiv:2211.01335 (2022)."},{"key":"e_1_3_2_1_52_1","volume-title":"CCF Conference on Big Data. Springer, 102-120","author":"Yu Hao","year":"2024","unstructured":"Hao Yu, Aoran Gan, Kai Zhang, Shiwei Tong, Qi Liu, and Zhaofeng Liu. 2024. Evaluation of retrieval-augmented generation: A survey. In CCF Conference on Big Data. Springer, 102-120."},{"key":"e_1_3_2_1_53_1","volume-title":"International conference on multimedia modeling. Springer, 374-386","author":"Zampoglou Markos","year":"2018","unstructured":"Markos Zampoglou, Foteini Markatopoulou, Gregoire Mercier, Despoina Touska, Evlampios Apostolidis, Symeon Papadopoulos, Roger Cozien, Ioannis Patras, Vasileios Mezaris, and Ioannis Kompatsiaris. 2018. Detecting tampered videos with multimedia forensics and deep learning. In International conference on multimedia modeling. Springer, 374-386."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642433"},{"key":"e_1_3_2_1_55_1","volume-title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP. arXiv:2403.15378","author":"Zhang Beichen","year":"2024","unstructured":"Beichen Zhang, Pan Zhang, Xiaoyi Dong, Yuhang Zang, and Jiaqi Wang. 2024c. Long-CLIP: Unlocking the Long-Text Capability of CLIP. arXiv:2403.15378 (2024)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681087"},{"key":"e_1_3_2_1_57_1","volume-title":"Vl-uncertainty: Detecting hallucination in large vision-language model via uncertainty estimation. arXiv:2411.11919","author":"Zhang Ruiyang","year":"2024","unstructured":"Ruiyang Zhang, Hu Zhang, and Zhedong Zheng. 2024b. Vl-uncertainty: Detecting hallucination in large vision-language model via uncertainty estimation. arXiv:2411.11919 (2024)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645680"},{"key":"e_1_3_2_1_59_1","volume-title":"VMID: A Multimodal Fusion LLM Framework for Detecting and Identifying Misinformation of Short Videos. arXiv:2411.10032","author":"Zhong Weihao","year":"2024","unstructured":"Weihao Zhong, Yinhao Xiao, Minghui Xu, and Xiuzhen Cheng. 2024. VMID: A Multimodal Fusion LLM Framework for Detecting and Identifying Misinformation of Short Videos. arXiv:2411.10032 (2024)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.744"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:25:24Z","timestamp":1783149924000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792362"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":60,"alternative-id":["10.1145\/3774904.3792362","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792362","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}