{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:05:01Z","timestamp":1772323501781,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3688984","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"11365-11369","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["MFMS: Learning Modality-Fused and Modality-Specific Features for Deepfake Detection and Localization Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0849-1381","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7634-9992","authenticated-orcid":false,"given":"Changtao","family":"Miao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5399-5545","authenticated-orcid":false,"given":"Man","family":"Luo","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8554-6886","authenticated-orcid":false,"given":"Jianshu","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4842-3390","authenticated-orcid":false,"given":"Wenzhong","family":"Deng","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1379-1830","authenticated-orcid":false,"given":"Weibin","family":"Yao","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0230-0501","authenticated-orcid":false,"given":"Zhe","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6482-2803","authenticated-orcid":false,"given":"Bingyu","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8761-0375","authenticated-orcid":false,"given":"Weiwei","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0026-6813","authenticated-orcid":false,"given":"Tao","family":"Gong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3028-0755","authenticated-orcid":false,"given":"Qi","family":"Chu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3689145"},{"key":"e_1_3_2_1_2_1","volume-title":"Munawar Hayat, Abhinav Dhall, and Kalin Stefanov.","author":"Cai Zhixi","year":"2023","unstructured":"Zhixi Cai, Shreya Ghosh, Aman Pankaj Adatia, Munawar Hayat, Abhinav Dhall, and Kalin Stefanov. 2023. AV-Deepfake1M: A large-scale LLM-driven audio-visual deepfake dataset. arXiv preprint arXiv:2311.15308 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103818"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"e_1_3_2_1_5_1","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. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Generative adversarial nets. Advances in neural information processing systems","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3476099.3484315"},{"key":"e_1_3_2_1_8_1","volume-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset. arXiv preprint arXiv:2108.05080","author":"Khalid Hasam","year":"2021","unstructured":"Hasam Khalid, Shahroz Tariq, Minha Kim, and Simon S Woo. 2021. FakeAVCeleb: A novel audio-video multimodal deepfake dataset. arXiv preprint arXiv:2108.05080 (2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680836233"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP53242.2021.9675331"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3119403"},{"key":"e_1_3_2_1_12_1","volume-title":"Multi-spectral Class Center Network for Face Manipulation Detection and Localization. arXiv preprint arXiv:2305.10794","author":"Miao Changtao","year":"2023","unstructured":"Changtao Miao, Qi Chu, Zhentao Tan, Zhenchao Jin, Wanyi Zhuang, Yue Wu, Bin Liu, Honggang Hu, and Nenghai Yu. 2023. Multi-spectral Class Center Network for Face Manipulation Detection and Localization. arXiv preprint arXiv:2305.10794 (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3233774"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3198275"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"e_1_3_2_1_16_1","volume-title":"Deepfake generation and detection: A benchmark and survey. arXiv preprint arXiv:2403.17881","author":"Pei Gan","year":"2024","unstructured":"Gan Pei, Jiangning Zhang, Menghan Hu, Guangtao Zhai, Chengjie Wang, Zhenyu Zhang, Jian Yang, Chunhua Shen, and Dacheng Tao. 2024. Deepfake generation and detection: A benchmark and survey. arXiv preprint arXiv:2403.17881 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 993--1000","author":"Raza Muhammad Anas","year":"2023","unstructured":"Muhammad Anas Raza and Khalid Mahmood Malik. 2023. Multimodaltrace: Deepfake detection using audiovisual representation learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 993--1000."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00667"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3214768"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_21_1","volume-title":"Internvideo: General video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191","author":"Wang Yi","year":"2022","unstructured":"Yi Wang, Kunchang Li, Yizhuo Li, Yinan He, Bingkun Huang, Zhiyu Zhao, Hongjie Zhang, Jilan Xu, Yi Liu, Zun Wang, et al. 2022. Internvideo: General video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191 (2022)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02136-1"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613767"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings, Part V. Springer, 391--407","author":"Zhuang Wanyi","year":"2022","unstructured":"Wanyi Zhuang, Qi Chu, Zhentao Tan, Qiankun Liu, Haojie Yuan, Changtao Miao, Zixiang Luo, and Nenghai Yu. 2022. UIA-ViT: Unsupervised inconsistency-aware method based on vision transformer for face forgery detection. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part V. Springer, 391--407."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859586"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688984","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3688984","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:29Z","timestamp":1750295849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688984"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":27,"alternative-id":["10.1145\/3664647.3688984","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3688984","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}