{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T17:10:04Z","timestamp":1781370604703,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the ARC Discovery Project","award":["DP220100800"],"award-info":[{"award-number":["DP220100800"]}]},{"name":"the ARC Discovery Early Career Researcher Award (DECRA)","award":["DE230100477"],"award-info":[{"award-number":["DE230100477"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,28]]},"DOI":"10.1145\/3696410.3714498","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T16:42:02Z","timestamp":1746463322000},"page":"5285-5296","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["MDAM\n            <sup>3<\/sup>\n            : A Misinformation Detection and Analysis Framework for Multitype Multimodal Media"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3752-7872","authenticated-orcid":false,"given":"Qingzheng","family":"Xu","sequence":"first","affiliation":[{"name":"The University of Queensland, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7391-0449","authenticated-orcid":false,"given":"Heming","family":"Du","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6716-610X","authenticated-orcid":false,"given":"Szymon","family":"\u0141ukasik","sequence":"additional","affiliation":[{"name":"AGH University of Science and Technology, Krak\u00f3w, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3411-7947","authenticated-orcid":false,"given":"Tianqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"City University of Macau, Macau, Macao"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5414-8276","authenticated-orcid":false,"given":"Sen","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0269-5649","authenticated-orcid":false,"given":"Xin","family":"Yu","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01452"},{"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 preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_3_1","unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716--23736."},{"key":"e_1_3_2_1_4_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_6_1","volume-title":"Giulia Boato, Michael Riegler, Yiannis Kompatsiaris, et al.","author":"Boididou Christina","year":"2015","unstructured":"Christina Boididou, Katerina Andreadou, Symeon Papadopoulos, Duc Tien Dang Nguyen, Giulia Boato, Michael Riegler, Yiannis Kompatsiaris, et al. 2015. Verifying multimedia use at mediaeval 2015. In MediaEval 2015. Vol. 1436. CEUR-WS."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_2_1_8_1","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877--1901."},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Machine Learning. PMLR, 2709--2720","author":"Casanova Edresson","year":"2022","unstructured":"Edresson Casanova, Julian Weber, Christopher D Shulby, Arnaldo Candido Junior, Eren G\u00f6lge, and Moacir A Ponti. 2022. Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone. In International Conference on Machine Learning. PMLR, 2709--2720."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413630"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Chung-Ming Chien Jheng-Hao Lin Chien-yu Huang Po-chun Hsu and Hung-yi Lee. 2021. Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech. In ICASSP 2021 - 2021 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). 8588--8592. https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9413880","DOI":"10.1109\/ICASSP39728.2021.9413880"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Dai Wenliang","year":"2024","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2024. InstructBLIP: towards general-purpose vision-language models with instruction tuning. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '23). Curran Associates Inc., Red Hook, NY, USA, Article 2142, 18 pages."},{"key":"e_1_3_2_1_13_1","volume-title":"Real time speech enhancement in the waveform domain. arXiv preprint arXiv:2006.12847","author":"Defossez Alexandre","year":"2020","unstructured":"Alexandre Defossez, Gabriel Synnaeve, and Yossi Adi. 2020. Real time speech enhancement in the waveform domain. arXiv preprint arXiv:2006.12847 (2020)."},{"key":"e_1_3_2_1_14_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In North American","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 North American Chapter of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:52967399"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00252"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_2"},{"key":"e_1_3_2_1_17_1","volume-title":"Bobby Tran, Mevan Babakar, et al.","author":"Dufour Nicholas","year":"2024","unstructured":"Nicholas Dufour, Arkanath Pathak, Pouya Samangouei, Nikki Hariri, Shashi Deshetti, Andrew Dudfield, Christopher Guess, Pablo Hern\u00e1ndez Escayola, Bobby Tran, Mevan Babakar, et al. 2024. AMMeBa: A Large-Scale Survey and Dataset of Media-Based Misinformation In-The-Wild. arXiv preprint arXiv:2405.11697 (2024)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00341"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"e_1_3_2_1_20_1","volume-title":"Armand Joulin, and Ishan Misra.","author":"Girdhar Rohit","year":"2023","unstructured":"Rohit Girdhar, Alaaeldin El-Nouby, Zhuang Liu, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, and Ishan Misra. 2023. ImageBind: One Embedding Space To Bind Them All. In CVPR."},{"key":"e_1_3_2_1_21_1","unstructured":"Google. 2024a. Google Cloud Vision API. https:\/\/cloud.google.com\/vision."},{"key":"e_1_3_2_1_22_1","unstructured":"Google. 2024b. Google Custom Search API. https:\/\/developers.google.com\/custom-search\/v1\/overview."},{"key":"e_1_3_2_1_23_1","unstructured":"Kung-Hsiang Huang Preslav Nakov Yejin Choi and Heng Ji. 2022. Faking Fake News for Real Fake News Detection: Propaganda-Loaded Training Data Generation. In Annual Meeting of the Association for Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:247359064"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123385"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01159"},{"key":"e_1_3_2_1_26_1","volume-title":"Yonghui Wu, et al.","author":"Jia Ye","year":"2018","unstructured":"Ye Jia, Yu Zhang, Ron Weiss, Quan Wang, Jonathan Shen, Fei Ren, Patrick Nguyen, Ruoming Pang, Ignacio Lopez Moreno, Yonghui Wu, et al. 2018. Transfer learning from speaker verification to multispeaker text-to-speech synthesis. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123454"},{"key":"e_1_3_2_1_28_1","volume-title":"Text2video-zero: Text-to-image diffusion models are zero-shot video generators. arXiv preprint arXiv:2303.13439","author":"Khachatryan Levon","year":"2023","unstructured":"Levon Khachatryan, Andranik Movsisyan, Vahram Tadevosyan, Roberto Henschel, Zhangyang Wang, Shant Navasardyan, and Humphrey Shi. 2023. Text2video-zero: Text-to-image diffusion models are zero-shot video generators. arXiv preprint arXiv:2303.13439 (2023)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313552"},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. PMLR, 5530--5540","author":"Kim Jaehyeon","year":"2021","unstructured":"Jaehyeon Kim, Jungil Kong, and Juhee Son. 2021. Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In International Conference on Machine Learning. PMLR, 5530--5540."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.158"},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Liu Haohe","year":"2023","unstructured":"Haohe Liu, Zehua Chen, Yi Yuan, Xinhao Mei, Xubo Liu, Danilo Mandic, Wenwu Wang, and Mark D Plumbley. 2023. AudioLDM: Text-to-Audio Generation with Latent Diffusion Models. Proceedings of the International Conference on Machine Learning (2023)."},{"key":"e_1_3_2_1_35_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024b. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_6"},{"key":"e_1_3_2_1_37_1","volume-title":"MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs. arXiv preprint arXiv:2406.08772","author":"Liu Xuannan","year":"2024","unstructured":"Xuannan Liu, Zekun Li, Peipei Li, Shuhan Xia, Xing Cui, Linzhi Huang, Huaibo Huang, Weihong Deng, and Zhaofeng He. 2024a. MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs. arXiv preprint arXiv:2406.08772 (2024)."},{"key":"e_1_3_2_1_38_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. arxiv","author":"Liu Yinhan","year":"1907","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: 1907.11692 [cs.CL] https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Grace Luo Trevor Darrell and Anna Rohrbach. 2021. NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media. In EMNLP.","DOI":"10.18653\/v1\/2021.emnlp-main.545"},{"key":"e_1_3_2_1_40_1","volume-title":"FACTIFY: A Multi-Modal Fact Verification Dataset.. In DE-FACTIFY@ AAAI.","author":"Mishra Shreyash","year":"2022","unstructured":"Shreyash Mishra, S Suryavardan, Amrit Bhaskar, Parul Chopra, Aishwarya N Reganti, Parth Patwa, Amitava Das, Tanmoy Chakraborty, Amit P Sheth, Asif Ekbal, et al. 2022. FACTIFY: A Multi-Modal Fact Verification Dataset.. In DE-FACTIFY@ AAAI."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Eric M\u00fcller-Budack Jonas Theiner Sebastian Diering Maximilian Idahl and Ralph Ewerth. 2020. Multimodal Analytics for Real-World News Using Measures of Cross-Modal Entity Consistency. In ACM ICMR.","DOI":"10.1145\/3372278.3390670"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference. 6149--6157","author":"Nakamura Kai","year":"2020","unstructured":"Kai Nakamura, Sharon Levy, and William Yang Wang. 2020. Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detection. In Proceedings of the Twelfth Language Resources and Evaluation Conference. 6149--6157."},{"key":"e_1_3_2_1_43_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Dan","unstructured":"Dan S. Nielsen and Ryan McConville. 2022. MuMiN: A Large-Scale Multilingual Multimodal Fact-Checked Misinformation Social Network Dataset. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (Madrid, Spain) (SIGIR '22). Association for Computing Machinery, New York, NY, USA, 3141--3153."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3592572.3592842"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-023-00312-6"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01240"},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning. PMLR, 28492--28518","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 International Conference on Machine Learning. PMLR, 28492--28518."},{"key":"e_1_3_2_1_50_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_51_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_52_1","volume-title":"International conference on machine learning. Pmlr, 8821--8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International conference on machine learning. Pmlr, 8821--8831."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Anton Razzhigaev Arseniy Shakhmatov Anastasia Maltseva Vladimir Arkhipkin Igor Pavlov Ilya Ryabov Angelina Kuts Alexander Panchenko Andrey Kuznetsov and Denis Dimitrov. 2023. Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion. arxiv: 2310.03502 [cs.CV]","DOI":"10.18653\/v1\/2023.emnlp-demo.25"},{"key":"e_1_3_2_1_54_1","volume-title":"Detecting and Grounding Multi-Modal Media Manipulation. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 6904--6913","author":"Rui Shao Tianxing Wu","year":"2023","unstructured":"Tianxing Wu Rui Shao and Ziwei Liu. 2023. Detecting and Grounding Multi-Modal Media Manipulation. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 6904--6913."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"Ekraam Sabir Wael AbdAlmageed Yue Wu and Prem Natarajan. 2018. Deep multimodal image repurposing detection. In ACM MM.","DOI":"10.1145\/3240508.3240707"},{"key":"e_1_3_2_1_56_1","volume-title":"Adversarial diffusion distillation. arXiv preprint arXiv:2311.17042","author":"Sauer Axel","year":"2023","unstructured":"Axel Sauer, Dominik Lorenz, Andreas Blattmann, and Robin Rombach. 2023. Adversarial diffusion distillation. arXiv preprint arXiv:2311.17042 (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367749"},{"key":"e_1_3_2_1_58_1","unstructured":"Xin Shen Heming Du Hongwei Sheng Shuyun Wang Hui Chen Huiqiang Chen Zhuojie Wu Xiaobiao Du Jiaying Ying Ruihan Lu Qingzheng Xu and Xin Yu. 2024. MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset. arxiv: 2410.19488 [cs.CV]"},{"key":"e_1_3_2_1_59_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems","author":"Shen Xin","year":"2023","unstructured":"Xin Shen, Shaozu Yuan, Hongwei Sheng, Heming Du, and Xin Yu. 2023. Auslan-Daily: Australian Sign Language Translation for Daily Communication and News. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/feb34ce77fc8b94c85d12e608b23ce67-Abstract-Datasets_and_Benchmarks.html"},{"key":"e_1_3_2_1_60_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"37","author":"Shivangi Aneja Chris Bregler","year":"2023","unstructured":"Chris Bregler Shivangi Aneja and Matthias Nie\u00dfner. 2023. COSMOS: Catching Out-of-Context Image Misuse Using Self-Supervised Learning. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 12 (2023), 14084--14092."},{"key":"e_1_3_2_1_61_1","volume-title":"Fakenewsnet: A data repository with news content, social context, and spatiotemporal information for studying fake news on social media. Big data","author":"Shu Kai","year":"2020","unstructured":"Kai Shu, Deepak Mahudeswaran, Suhang Wang, Dongwon Lee, and Huan Liu. 2020. Fakenewsnet: A data repository with news content, social context, and spatiotemporal information for studying fake news on social media. Big data, Vol. 8, 3 (2020), 171--188."},{"key":"e_1_3_2_1_62_1","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Song Kaitao","year":"2020","unstructured":"Kaitao Song, Xu Tan, Tao Qin, Jianfeng Lu, and Tie-Yan Liu. 2020. MPNet: masked and permuted pre-training for language understanding. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS '20). Curran Associates Inc., Red Hook, NY, USA, Article 1414, 11 pages."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1322"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.163"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"e_1_3_2_1_66_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov et al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv: 2307.09288 [cs.CL]"},{"key":"e_1_3_2_1_67_1","unstructured":"Ben Wang and Aran Komatsuzaki. 2021. GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model. https:\/\/github.com\/kingoflolz\/mesh-transformer-jax."},{"key":"e_1_3_2_1_68_1","volume-title":"Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571","author":"Wang Jiuniu","year":"2023","unstructured":"Jiuniu Wang, Hangjie Yuan, Dayou Chen, Yingya Zhang, Xiang Wang, and Shiwei Zhang. 2023. Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01109"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219903"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00126"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104205"},{"key":"e_1_3_2_1_76_1","volume-title":"MMooc: A Multimodal Misinformation Dataset for Out-of-Context News Analysis. In Australasian Conference on Information Security and Privacy (Lecture Notes in Computer Science). Springer, 444--459","author":"Xu Qingzheng","year":"2024","unstructured":"Qingzheng Xu, Heming Du, Huiqiang Chen, Bo Liu, and Xin Yu. 2024b. MMooc: A Multimodal Misinformation Dataset for Out-of-Context News Analysis. In Australasian Conference on Information Security and Privacy (Lecture Notes in Computer Science). Springer, 444--459."},{"key":"e_1_3_2_1_77_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13040--13051","author":"Ye Qinghao","year":"2024","unstructured":"Qinghao Ye, Haiyang Xu, Jiabo Ye, Ming Yan, Anwen Hu, Haowei Liu, Qi Qian, Ji Zhang, and Fei Huang. 2024. mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13040--13051."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00355"},{"key":"e_1_3_2_1_79_1","volume-title":"Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific","author":"Zhang Xuan","unstructured":"Xuan Zhang and Wei Gao. 2023. Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), Jong C. Park, Yuki Arase, Baotian Hu, Wei Lu, Derry Wijaya, Ayu Purwarianti, and Adila Alfa Krisnadhi (Eds.). Association for Computational Linguistics, Nusa Dua, Bali, 996--1011."},{"key":"e_1_3_2_1_80_1","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)."},{"key":"e_1_3_2_1_81_1","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"Zlatkova Dimitrina","year":"2099","unstructured":"Dimitrina Zlatkova, Preslav Nakov, and Ivan Koychev. 2019. Fact-Checking Meets Fauxtography: Verifying Claims About Images. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan (Eds.). Association for Computational Linguistics, Hong Kong, China, 2099--2108."}],"event":{"name":"WWW '25: The ACM Web Conference 2025","location":"Sydney NSW Australia","acronym":"WWW '25","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714498","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:32Z","timestamp":1750295912000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":81,"alternative-id":["10.1145\/3696410.3714498","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714498","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}