{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T11:26:54Z","timestamp":1764588414866,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union?s Horizon 2020 research and innovation program under the Marie Sk?odowska- Curie","award":["812997"],"award-info":[{"award-number":["812997"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,12]]},"DOI":"10.1145\/3591106.3592230","type":"proceedings-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T22:33:38Z","timestamp":1686263618000},"page":"581-585","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Improving Generalization for Multimodal Fake News Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4784-7391","authenticated-orcid":false,"given":"Sahar","family":"Tahmasebi","sequence":"first","affiliation":[{"name":"TIB - Leibniz Information Centre for Science and Technology, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7421-6213","authenticated-orcid":false,"given":"Sherzod","family":"Hakimov","sequence":"additional","affiliation":[{"name":"University of Potsdam, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0918-6297","authenticated-orcid":false,"given":"Ralph","family":"Ewerth","sequence":"additional","affiliation":[{"name":"TIB - Leibniz Information Centre for Science and Technology, Germany and L3S Research Center, Leibniz University of Hannover, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6802-1241","authenticated-orcid":false,"given":"Eric","family":"M\u00fcller-Budack","sequence":"additional","affiliation":[{"name":"TIB - Leibniz Information Centre for Science and Technology, Germany and L3S Research Center, Leibniz University of Hannover, Germany"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1257\/jep.31.2.211"},{"key":"e_1_3_2_1_2_1","volume-title":"Verifying Multimedia Use at MediaEval","author":"Boididou Christina","year":"2015","unstructured":"Christina Boididou, Katerina Andreadou, Symeon Papadopoulos, Duc-Tien Dang-Nguyen, Giulia Boato, Michael Riegler, and Yiannis Kompatsiaris. 2015. Verifying Multimedia Use at MediaEval 2015. 1436 (2015). http:\/\/ceur-ws.org\/Vol-1436\/Paper4.pdf"},{"key":"e_1_3_2_1_3_1","volume-title":"Verifying Multimedia Use at MediaEval","author":"Boididou Christina","year":"2016","unstructured":"Christina Boididou, Symeon Papadopoulos, Duc-Tien Dang-Nguyen, Giulia Boato, Michael Riegler, Stuart\u00a0E. Middleton, Andreas Petlund, and Yiannis Kompatsiaris. 2016. Verifying Multimedia Use at MediaEval 2016. 1739 (2016). http:\/\/ceur-ws.org\/Vol-1739\/MediaEval_2016_paper_3.pdf"},{"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":"10.18653\/v1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_7_1","volume-title":"Gaussian Error Linear Units (GELUs). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian Error Linear Units (GELUs). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_8_1","volume-title":"spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing. To appear 7, 1","author":"Honnibal Matthew","year":"2017","unstructured":"Matthew Honnibal and Ines Montani. 2017. spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing. To appear 7, 1 (2017), 411\u2013420."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123454"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313552"},{"key":"e_1_3_2_1_11_1","first-page":"40","volume-title":"NeurIPS 2019 Workshop","author":"Kiela Douwe","year":"2019","unstructured":"Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, and Davide Testuggine. 2019. Supervised Multimodal Bitransformers for Classifying Images and Text. In Visually Grounded Interaction and Language (ViGIL), NeurIPS 2019 Workshop, Vancouver, Canada, December 13, 2019. https:\/\/vigilworkshop.github.io\/static\/papers\/40.pdf"},{"key":"e_1_3_2_1_12_1","volume-title":"Benchmark and Challenges in Entity-aware Image Captioning. CoRR abs\/2010.03743","author":"Liu Fuxiao","year":"2020","unstructured":"Fuxiao Liu, Yinghan Wang, Tianlu Wang, and Vicente Ordonez. 2020. VisualNews : Benchmark and Challenges in Entity-aware Image Captioning. CoRR abs\/2010.03743 (2020). arXiv:2010.03743https:\/\/arxiv.org\/abs\/2010.03743"},{"key":"e_1_3_2_1_13_1","volume-title":"Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning, ICML 2021","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event(Proceedings of Machine Learning Research, Vol.\u00a0139). PMLR, 8748\u20138763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Learning Representations, ICLR","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06086-4"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524650"},{"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":"10.1145\/3219819.3219903"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206973"}],"event":{"name":"ICMR '23: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Thessaloniki Greece","acronym":"ICMR '23"},"container-title":["Proceedings of the 2023 ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592230","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591106.3592230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:22Z","timestamp":1750182682000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":20,"alternative-id":["10.1145\/3591106.3592230","10.1145\/3591106"],"URL":"https:\/\/doi.org\/10.1145\/3591106.3592230","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"}}]}}