{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:08:39Z","timestamp":1776888519843,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,12]]},"DOI":"10.1145\/3591106.3592271","type":"proceedings-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T22:33:38Z","timestamp":1686263618000},"page":"343-352","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":54,"title":["Multi-modal Fake News Detection on Social Media via Multi-grained Information Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0762-7677","authenticated-orcid":false,"given":"Yangming","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Computer Science, Fudan University, China and Key Laboratory of Culture & Tourism Intelligent Computing of Ministry of Culture & Tourism, Fudan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6957-7682","authenticated-orcid":false,"given":"Yuzhou","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, China and Key Laboratory of Culture & Tourism Intelligent Computing of Ministry of Culture & Tourism, Fudan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6527-2424","authenticated-orcid":false,"given":"Qichao","family":"Ying","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, China and Key Laboratory of Culture & Tourism Intelligent Computing of Ministry of Culture & Tourism, Fudan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5224-6374","authenticated-orcid":false,"given":"Zhenxing","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, China and Key Laboratory of Culture & Tourism Intelligent Computing of Ministry of Culture & Tourism, Fudan University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5867-1315","authenticated-orcid":false,"given":"Xinpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Fudan University, China and Key Laboratory of Culture & Tourism Intelligent Computing of Ministry of Culture & Tourism, Fudan University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"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":"Like Article","author":"Allein Liesbeth","year":"2021","unstructured":"Liesbeth Allein, Marie-Francine Moens, and Domenico Perrotta. 2021. Like Article, Like Audience: Enforcing Multimodal Correlations for Disinformation Detection. arXiv preprint arXiv:2108.13892 (2021)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191577"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5393"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-017-0143-x"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511968"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/pra2.2015.145052010082"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00160"},{"key":"e_1_3_2_1_11_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_12_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 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_13_1","volume-title":"Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921","author":"Gu Xiuye","year":"2021","unstructured":"Xiuye Gu, Tsung-Yi Lin, Weicheng Kuo, and Yin Cui. 2021. Open-vocabulary object detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123454"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/07317131.2012.650971"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313552"},{"key":"e_1_3_2_1_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_18_1","volume-title":"Language-driven semantic segmentation. arXiv preprint arXiv:2201.03546","author":"Li Boyi","year":"2022","unstructured":"Boyi Li, Kilian\u00a0Q Weinberger, Serge Belongie, Vladlen Koltun, and Ren\u00e9 Ranftl. 2022. Language-driven semantic segmentation. arXiv preprint arXiv:2201.03546 (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_20_1","volume-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in Neural Information Processing Systems 32","author":"Lu Jiasen","year":"2019","unstructured":"Jiasen Lu, Dhruv Batra, Devi Parikh, and Stefan Lee. 2019. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence. 3818\u20133824","author":"Ma Jing","year":"2016","unstructured":"Jing Ma, Wei Gao, Prasenjit Mitra, Sejeong Kwon, Bernard\u00a0J Jansen, Kam-Fai Wong, and Meeyoung Cha. 2016. Detecting rumors from microblogs with recurrent neural networks. In Proceedings of the International Joint Conference on Artificial Intelligence. 3818\u20133824."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390670"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482139"},{"key":"e_1_3_2_1_24_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_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481548"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00062"},{"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":"Proceedings of the International Conference on Machine Learning. 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning. 8748\u20138763."},{"key":"e_1_3_2_1_29_1","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683","author":"Raffel Colin","year":"2019","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter\u00a0J Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1089\/big.2020.0062"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i10.7230"},{"key":"e_1_3_2_1_32_1","volume-title":"Leveraging Intra and Inter Modality Relationship for Multimodal Fake News Detection. In Companion Proceedings of The Web Conference. 726\u2013734","author":"Singhal Shivangi","year":"2022","unstructured":"Shivangi Singhal, Tanisha Pandey, Saksham Mrig, Rajiv\u00a0Ratn Shah, and Ponnurangam Kumaraguru. 2022. Leveraging Intra and Inter Modality Relationship for Multimodal Fake News Detection. In Companion Proceedings of The Web Conference. 726\u2013734."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2019.00-44"},{"key":"e_1_3_2_1_34_1","volume-title":"Visualizing data using t-SNE.Journal of Machine Learning Research 9, 11","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of Machine Learning Research 9, 11 (2008)."},{"key":"e_1_3_2_1_35_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219903"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390713"},{"key":"e_1_3_2_1_38_1","volume-title":"Hairclip: Design your hair by text and reference image. arXiv preprint arXiv:2112.05142","author":"Wei Tianyi","year":"2021","unstructured":"Tianyi Wei, Dongdong Chen, Wenbo Zhou, Jing Liao, Zhentao Tan, Lu Yuan, Weiming Zhang, and Nenghai Yu. 2021. Hairclip: Design your hair by text and reference image. arXiv preprint arXiv:2112.05142 (2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.226"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102610"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16428"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25670"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Feng Yu Qiang Liu Shu Wu Liang Wang Tieniu Tan 2017. A Convolutional Approach for Misinformation Identification.. In IJCAI. 3901\u20133907.","DOI":"10.24963\/ijcai.2017\/545"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450004"},{"key":"e_1_3_2_1_45_1","volume-title":"SAFE: Similarity-Aware Multi-modal Fake News Detection. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 354\u2013367","author":"Zhou Xinyi","year":"2020","unstructured":"Xinyi Zhou, Jindi Wu, and Reza Zafarani. 2020. SAFE: Similarity-Aware Multi-modal Fake News Detection. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 354\u2013367."},{"key":"e_1_3_2_1_46_1","volume-title":"Multimodal fake news detection via CLIP-guided learning. arXiv preprint arXiv:2205.14304","author":"Zhou Yangming","year":"2022","unstructured":"Yangming Zhou, Yuzhou Yang, Qichao Ying, Zhenxing Qian, and Xinpeng Zhang. 2022. Multimodal fake news detection via CLIP-guided learning. arXiv preprint arXiv:2205.14304 (2022)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3185151"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3161603"}],"event":{"name":"ICMR '23: International Conference on Multimedia Retrieval","location":"Thessaloniki Greece","acronym":"ICMR '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2023 ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592271","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591106.3592271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:30Z","timestamp":1750178250000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592271"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":48,"alternative-id":["10.1145\/3591106.3592271","10.1145\/3591106"],"URL":"https:\/\/doi.org\/10.1145\/3591106.3592271","relation":{},"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}