{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T05:50:40Z","timestamp":1782453040969,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":70,"publisher":"ACM","funder":[{"name":"Chinese National Natural Science Foundation Projects","award":["U23B2054,62276254,62306313"],"award-info":[{"award-number":["U23B2054,62276254,62306313"]}]},{"name":"the Beijing Science and Technology Plan Project","award":["Z231100005923033"],"award-info":[{"award-number":["Z231100005923033"]}]},{"name":"Beijing Natural Science Foundation","award":["L221013"],"award-info":[{"award-number":["L221013"]}]},{"name":"the Science and Technology Development Fund of Macau Project","award":["0140\/2024\/AGJ"],"award-info":[{"award-number":["0140\/2024\/AGJ"]}]},{"name":"InnoHK program"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755592","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"4768-4777","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["WMamba: Wavelet-based Mamba for Face Forgery Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3983-5596","authenticated-orcid":false,"given":"Siran","family":"Peng","sequence":"first","affiliation":[{"name":"MAIS, CASIA, Beijing, China and SAI, UCAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3199-9261","authenticated-orcid":false,"given":"Tianshuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"SAI, UCAS, Beijing, China and MAIS, CASIA, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3726-248X","authenticated-orcid":false,"given":"Li","family":"Gao","sequence":"additional","affiliation":[{"name":"CMFT Co., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4636-9677","authenticated-orcid":false,"given":"Xiangyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"MAIS, CASIA, Beijing, China and SAI, UCAS, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9447-0365","authenticated-orcid":false,"given":"Haoyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"SAI, UCAS, Beijing, China and MAIS, CASIA, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1668-058X","authenticated-orcid":false,"given":"Kai","family":"Pang","sequence":"additional","affiliation":[{"name":"Guangzhou Pixel Solutions Co., Ltd., Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0791-189X","authenticated-orcid":false,"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"MAIS, CASIA, Beijing, China, SAI, UCAS, Beijing, China, CAIR, HKSIS, CAS, Hong Kong, China, and SCSE, FIE, M.U.S.T, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02367"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"e_1_3_2_1_3_1","volume-title":"Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection. arXiv preprint arXiv:2411.19715","author":"Cui Xinjie","year":"2024","unstructured":"Xinjie Cui, Yuezun Li, Ao Luo, Jiaran Zhou, and Junyu Dong. 2024. Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection. arXiv preprint arXiv:2411.19715 (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","volume-title":"The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397","author":"Dolhansky Brian","year":"2020","unstructured":"Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, and Cristian Canton Ferrer. 2020. The deepfake detection challenge (dfdc) dataset. arXiv preprint arXiv:2006.07397 (2020)."},{"key":"e_1_3_2_1_7_1","volume-title":"The deepfake detection challenge (dfdc) preview dataset. arXiv preprint arXiv:1910.08854","author":"Dolhansky Brian","year":"2019","unstructured":"Brian Dolhansky, Russ Howes, Ben Pflaum, Nicole Baram, and Cristian Canton Ferrer. 2019. The deepfake detection challenge (dfdc) preview dataset. arXiv preprint arXiv:1910.08854 (2019)."},{"key":"e_1_3_2_1_8_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_9_1","volume-title":"International Conference on Learning Representation (ICLR).","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representation (ICLR)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32312"},{"key":"e_1_3_2_1_11_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475508"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19955"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_35"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00308"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1573-4412(05)80019-4"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803740"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00072"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19978"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3086109"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00048"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01921"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00639"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547832"},{"key":"e_1_3_2_1_28_1","volume-title":"Faceshifter: Towards high fidelity and occlusion aware face swapping. arXiv preprint arXiv:1912.13457","author":"Li Lingzhi","year":"2019","unstructured":"Lingzhi Li, Jianmin Bao, Hao Yang, Dong Chen, and Fang Wen. 2019. Faceshifter: Towards high fidelity and occlusion aware face swapping. arXiv preprint arXiv:1912.13457 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the Asian Conference on Computer Vision (ACCV). 1858-1874","author":"Liu Jie","year":"2022","unstructured":"Jie Liu, Jingjing Wang, Peng Zhang, Chunmao Wang, Di Xie, and Shiliang Pu. 2022b. Multi-Scale Wavelet Transformer for Face Forgery Detection. In Proceedings of the Asian Conference on Computer Vision (ACCV). 1858-1874."},{"key":"e_1_3_2_1_31_1","first-page":"103031","article-title":"VMamba: Visual State Space Model","volume":"37","author":"Liu Yue","year":"2024","unstructured":"Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, Yaowei Wang, Qixiang Ye, Jianbin Jiao, and Yunfan Liu. 2024. VMamba: Visual State Space Model. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 37. 103031-103063.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_34_1","volume-title":"Decoupled Weight Decay Regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled Weight Decay Regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_35_1","volume-title":"Detecting GAN-Generated Imagery Using Saturation Cues. In 2019 IEEE International Conference on Image Processing (ICIP). 4584-4588","author":"McCloskey Scott","year":"2019","unstructured":"Scott McCloskey and Michael Albright. 2019. Detecting GAN-Generated Imagery Using Saturation Cues. In 2019 IEEE International Conference on Image Processing (ICIP). 4584-4588."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3233774"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01647"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00728"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20765"},{"key":"e_1_3_2_1_40_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, Zhenyu Zhang, Chengjie Wang, Yunsheng Wu, Guangtao Zhai, 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_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3381823"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00558"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00702"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW65960.2025.00177"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16367"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20130"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28310"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"e_1_3_2_1_54_1","volume-title":"Proceedings of The 18th European Conference on Computer Vision (ECCV). 402-419","author":"Tian Jiahe","year":"2024","unstructured":"Jiahe Tian, Cai Yu, Xi Wang, Peng Chen, Zihao Xiao, Jiao Dai, Jizhong Han, and Yesheng Chai. 2024. Real Appearance Modeling for\u00a0More General Deepfake Detection. In Proceedings of The 18th European Conference on Computer Vision (ECCV). 402-419."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681179"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02071"},{"key":"e_1_3_2_1_57_1","volume-title":"Towards Generalizable Deepfake Video Detection with Thumbnail Layout and Graph Reasoning. arXiv preprint arXiv:2403.10261","author":"Xu Yuting","year":"2024","unstructured":"Yuting Xu, Jian Liang, Lijun Sheng, and Xiao-Yu Zhang. 2024. Towards Generalizable Deepfake Video Detection with Thumbnail Layout and Graph Reasoning. arXiv preprint arXiv:2403.10261 (2024)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00858"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02048"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3249566"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146781"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02046"},{"key":"e_1_3_2_1_63_1","volume-title":"Proceedings of The 18th European Conference on Computer Vision (ECCV). Springer, 407-424","author":"Zhang Daichi","year":"2024","unstructured":"Daichi Zhang, Zihao Xiao, Shikun Li, Fanzhao Lin, Jianmin Li, and Shiming Ge. 2024. Learning natural consistency representation for face forgery video detection. In Proceedings of The 18th European Conference on Computer Vision (ECCV). Springer, 407-424."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01475"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"e_1_3_2_1_67_1","first-page":"44965","article-title":"FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge","volume":"37","author":"Zhou Jiaran","year":"2024","unstructured":"Jiaran Zhou, Yuezun Li, Baoyuan Wu, Bin Li, Junyu Dong, et al., 2024. FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge. In Advances in Neural Information Processing Systems (NeurIPS), Vol. 37. 44965-44988.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00572"},{"key":"e_1_3_2_1_69_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML). Article 2584","author":"Zhu Lianghui","year":"2024","unstructured":"Lianghui Zhu, Bencheng Liao, Qian Zhang, Xinlong Wang, Wenyu Liu, and Xinggang Wang. 2024. Vision mamba: efficient visual representation learning with bidirectional state space model. In Proceedings of the 41st International Conference on Machine Learning (ICML). Article 2584, 14 pages."},{"key":"e_1_3_2_1_70_1","volume-title":"Better Results. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Zhu Xizhou","year":"2019","unstructured":"Xizhou Zhu, Han Hu, Stephen Lin, and Jifeng Dai. 2019. Deformable ConvNets V2: More Deformable, Better Results. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:06:20Z","timestamp":1765310780000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755592"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":70,"alternative-id":["10.1145\/3746027.3755592","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755592","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}