{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:26:04Z","timestamp":1781587564579,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733400","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:39Z","timestamp":1750876299000},"page":"1145-1153","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Multi-modal Similarity Guided Adaptive Fusion Network for Short Video Fake News Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3720-7265","authenticated-orcid":false,"given":"Jing","family":"Shen","sequence":"first","affiliation":[{"name":"Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5119-6464","authenticated-orcid":false,"given":"Yanjia","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8606-8419","authenticated-orcid":false,"given":"Shengze","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8781-976X","authenticated-orcid":false,"given":"Yuping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4837-9956","authenticated-orcid":false,"given":"Haibo","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612426"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680663"},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511968"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482212"},{"key":"e_1_3_2_1_6_1","volume-title":"Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116","author":"Conneau Alexis","year":"2019","unstructured":"Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzm\u00e1n, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2019)."},{"key":"e_1_3_2_1_7_1","unstructured":"Dhanvi Ganti. 2022. A Novel Method for Detecting Misinformation in Videos Utilizing Reverse Image Search Semantic Analysis and Sentiment Comparison of Metadata. https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4128499."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"e_1_3_2_1_9_1","volume-title":"Fake news on Twitter during the 2016 US presidential election. Science 363, 6425","author":"Grinberg Nir","year":"2019","unstructured":"Nir Grinberg, Kenneth Joseph, Lisa Friedland, Briony Swire-Thompson, and David Lazer. 2019. Fake news on Twitter during the 2016 US presidential election. Science 363, 6425 (2019), 374--378."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"e_1_3_2_1_11_1","volume-title":"Jort F Gemmeke, Aren Jansen, R Channing Moore, Manoj Plakal, Devin Platt, Rif A Saurous, Bryan Seybold, et al.","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."},{"key":"e_1_3_2_1_12_1","volume-title":"Towards Automatic Detection of Misinformation in Online Medical Videos. In 2019 International Conference on Multimodal Interaction. 235--243","author":"Hou Rui","year":"2019","unstructured":"Rui Hou, Ver\u00f3nica P\u00e9rez-Rosas, Stacy Loeb, and Rada Mihalcea. 2019. Towards Automatic Detection of Misinformation in Online Medical Videos. In 2019 International Conference on Multimodal Interaction. 235--243."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1080\/07317131.2012.650971"},{"key":"e_1_3_2_1_14_1","volume-title":"Supervised contrastive learning. Advances in neural information processing systems 33","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, ChenWang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems 33 (2020), 18661--18673."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-17208-6"},{"key":"e_1_3_2_1_16_1","volume-title":"Social Media and Technology","author":"Michelle Faverio Olivia Sidoti","year":"2024","unstructured":"Olivia Sidoti Michelle Faverio. 2024. Teens, Social Media and Technology 2024. https:\/\/www.pewresearch.org\/internet\/2024\/12\/12\/teens-social-mediaand-technology-2024\/."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1080\/23738871.2018.1462395"},{"key":"e_1_3_2_1_18_1","unstructured":"Nic Newman. 2023. Overview and key findings of the 2023 Digital News Report. https:\/\/reutersinstitute.politics.ox.ac.uk\/digital-news-report\/2023\/dnrexecutive- summary."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544549.3573809"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10796-022-10242-z"},{"key":"e_1_3_2_1_21_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1108\/OIR-03-2018-0101"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078897.3080535"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26689"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481548"},{"key":"e_1_3_2_1_26_1","volume-title":"Two heads are better than one: Improving fake news video detection by correlating with neighbors. arXiv preprint arXiv:2306.05241","author":"Qi Peng","year":"2023","unstructured":"Peng Qi, Yuyang Zhao, Yufeng Shen, Wei Ji, Juan Cao, and Tat-Seng Chua. 2023. Two heads are better than one: Improving fake news video detection by correlating with neighbors. arXiv preprint arXiv:2306.05241 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462871"},{"key":"e_1_3_2_1_28_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Machine Learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 1st Workshop on NLP for COVID-19 at ACL","author":"Medina Serrano Juan Carlos","year":"2020","unstructured":"Juan Carlos Medina Serrano, Orestis Papakyriakopoulos, and Simon Hegelich. 2020. NLP-based feature extraction for the detection of COVID-19 misinformation videos on YouTube. In Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671928"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671928"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3137597.3137600"},{"key":"e_1_3_2_1_34_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_35_1","volume-title":"Misinformation detection in social media video posts. arXiv preprint arXiv:2202.07706","author":"Wang Kehan","year":"2022","unstructured":"Kehan Wang, David Chan, Seth Z Zhao, John Canny, and Avideh Zakhor. 2022. Misinformation detection in social media video posts. arXiv preprint arXiv:2202.07706 (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING","author":"Wu Kaixuan","year":"2024","unstructured":"Kaixuan Wu, Yanghao Lin, Donglin Cao, and Dazhen Lin. 2024. Interpretable Short Video Rumor Detection Based on Modality Tampering. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 9180--9189."},{"key":"e_1_3_2_1_37_1","first-page":"2560","article-title":"Multimodal fusion with co-attention networks for fake news detection. In Findings of the association for computational linguistics","volume":"2021","author":"Wu Yang","year":"2021","unstructured":"Yang Wu, Pengwei Zhan, Yunjian Zhang, Liming Wang, and Zhen Xu. 2021. Multimodal fusion with co-attention networks for fake news detection. In Findings of the association for computational linguistics: ACL-IJCNLP 2021. 2560--2569.","journal-title":"ACL-IJCNLP"},{"key":"e_1_3_2_1_38_1","volume-title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision). arXiv preprint arXiv:2309.17421","author":"Yang Zhengyuan","year":"2023","unstructured":"Zhengyuan Yang, Linjie Li, Kevin Lin, Jianfeng Wang, Chung-Ching Lin, Zicheng Liu, and Lijuan Wang. 2023. The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision). arXiv preprint arXiv:2309.17421 (2023)."},{"key":"e_1_3_2_1_39_1","unstructured":"Yuan Yao Tianyu Yu Ao Zhang Chongyi Wang Junbo Cui Hongji Zhu Tianchi Cai Haoyu Li Weilin Zhao Zhihui He et al. 2024. MiniCPM-V: A GPT-4V Level MLLM on Your Phone. arXiv preprint arXiv:2408.01800 (2024)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25670"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681673"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.03.004"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592271"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733400","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:12:14Z","timestamp":1755749534000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733400"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":43,"alternative-id":["10.1145\/3731715.3733400","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733400","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}