{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:18:21Z","timestamp":1775607501084,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972047,62372060"],"award-info":[{"award-number":["61972047,62372060"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSFC-General Technology Basic Research Joint Funds","award":["U1936220"],"award-info":[{"award-number":["U1936220"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658118","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"666-674","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Intra and Inter-modality Incongruity Modeling and Adversarial Contrastive Learning for Multimodal Fake News Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5824-9445","authenticated-orcid":false,"given":"Siqi","family":"Wei","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7112-126X","authenticated-orcid":false,"given":"Bin","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the International Conference on Computational Linguistics. 6625--6643","author":"Alam Firoj","year":"2022","unstructured":"Firoj Alam, Stefano Cresci, Tanmoy Chakraborty, Fabrizio Silvestri, Dimiter Dimitrov, Giovanni Da San Martino, Shaden Shaar, Hamed Firooz, and Preslav Nakov. 2022. A Survey on Multimodal Disinformation Detection. In Proceedings of the International Conference on Computational Linguistics. 6625--6643."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-017-0143-x"},{"key":"e_1_3_2_1_3_1","first-page":"3144","article-title":"Is multi-modal necessarily better? Robustness evaluation of multi-modal fake news detection","volume":"10","author":"Chen Jinyin","year":"2023","unstructured":"Jinyin Chen, Chengyu Jia, Haibin Zheng, Ruoxi Chen, and Chenbo Fu. 2023. Is multi-modal necessarily better? Robustness evaluation of multi-modal fake news detection. IEEE Transactions on Network Science and Engineering, Vol. 10, 6 (2023), 3144--3158.","journal-title":"IEEE Transactions on Network Science and Engineering"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the International Conference on Learning Representations. 1--21","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, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proceedings of the International Conference on Learning Representations. 1--21."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.09.001"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123454"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics. 4171--4186","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics. 4171--4186."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313552"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the International Conference on Learning Representations. 1--15","author":"Kingma Diederik P","year":"2015","unstructured":"Diederik P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations. 1--15."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the International Conference on Learning Representations. 1--11","author":"Miyato Takeru","year":"2016","unstructured":"Takeru Miyato, Andrew M Dai, and Ian Goodfellow. 2016. Adversarial Training Methods for Semi-Supervised Text Classification. In Proceedings of the International Conference on Learning Representations. 1--11."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-021-00873-8"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462871"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1089\/big.2020.0062"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3137597.3137600"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the International Conference on Learning Representations. 1--14","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proceedings of the International Conference on Learning Representations. 1--14."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i10.7230"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2019.00-44"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102437"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.00038"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Proceedings of the Conference on Neural Information Processing Systems , Vol. 30 (2017), 5998--6008."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3263552"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219903"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.226"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.04.022"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems. 9330--9343","author":"Xing Yue","year":"2022","unstructured":"Yue Xing, Qifan Song, and Guang Cheng. 2022. Phase Transition from Clean Training to Adversarial Training. In Proceedings of the Conference on Neural Information Processing Systems. 9330--9343."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102610"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the Conference on Neural Information Processing Systems. 1--18","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. In Proceedings of the Conference on Neural Information Processing Systems. 1--18."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482196"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-47436-2_27"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3291382"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00480"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658118","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:52:04Z","timestamp":1755766324000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":33,"alternative-id":["10.1145\/3652583.3658118","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658118","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}