{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T13:18:31Z","timestamp":1782825511551,"version":"3.54.5"},"reference-count":58,"publisher":"Association for Computing Machinery (ACM)","issue":"2s","license":[{"start":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T00:00:00Z","timestamp":1656547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Plan","award":["2020AAA0140001"],"award-info":[{"award-number":["2020AAA0140001"]}]},{"name":"Beijing Natural Science Foundation","award":["19L2040"],"award-info":[{"award-number":["19L2040"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61772513"],"award-info":[{"award-number":["61772513"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association, Chinese Academy of Sciences","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2022,6,30]]},"abstract":"<jats:p>Increasingly advanced deepfake approaches have made the detection of deepfake videos very challenging. We observe that the general deepfake videos often exhibit appearance-level temporal inconsistencies in some facial components between frames, resulting in discriminative spatiotemporal latent patterns among semantic-level feature maps. Inspired by this finding, we propose a predictive representative learning approach termed Latent Pattern Sensing to capture these semantic change characteristics for deepfake video detection. The approach cascades a Convolution Neural Network-based encoder, a ConvGRU-based aggregator, and a single-layer binary classifier. The encoder and aggregator are pretrained in a self-supervised manner to form the representative spatiotemporal context features. Then, the classifier is trained to classify the context features, distinguishing fake videos from real ones. Finally, we propose a selective self-distillation fine-tuning method to further improve the robustness and performance of the detector. In this manner, the extracted features can simultaneously describe the latent patterns of videos across frames spatially and temporally in a unified way, leading to an effective and robust deepfake video detector. Extensive experiments and comprehensive analysis prove the effectiveness of our approach, e.g., achieving a very highest Area Under Curve (AUC) score of 99.94% on FaceForensics++ benchmark and surpassing 12 states of the art at least 7.90%@AUC and 8.69%@AUC on challenging DFDC and Celeb-DF(v2) benchmarks, respectively.<\/jats:p>","DOI":"10.1145\/3536426","type":"journal-article","created":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T12:39:22Z","timestamp":1652704762000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":55,"title":["Deepfake Video Detection via Predictive Representation Learning"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5293-310X","authenticated-orcid":false,"given":"Shiming","family":"Ge","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0339-9400","authenticated-orcid":false,"given":"Fanzhao","family":"Lin","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1516-6276","authenticated-orcid":false,"given":"Chenyu","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5377-964X","authenticated-orcid":false,"given":"Daichi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8618-4992","authenticated-orcid":false,"given":"Weiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1300-1769","authenticated-orcid":false,"given":"Dan","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Shanghai University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,6]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00338"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"e_1_3_2_5_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201916)","author":"Ballas Nicolas","year":"2016","unstructured":"Nicolas Ballas, Li Yao, Chris Pal, and Aaron Courville. 2016. Delving deeper into convolutional networks for learning video representations. In Proceedings of the International Conference on Learning Representations (ICLR\u201916)."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2980194"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258880"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.5555\/184656.180369"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024164"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00421"},{"key":"e_1_3_2_12_2","first-page":"4417","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201917)","author":"Denton Emily","year":"2017","unstructured":"Emily Denton and Vighnesh Birodkar. 2017. Unsupervised learning of disentangled representations from video. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201917). 4417\u20134426."},{"key":"e_1_3_2_13_2","article-title":"The deepfake detection challenge (dfdc) preview dataset","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:1910.08854. Retrieved from https:\/\/arxiv.org\/abs\/1910.08854.","journal-title":"arXiv:1910.08854"},{"key":"e_1_3_2_14_2","first-page":"3233","volume-title":"Proceedings of the International Conference on Machine Learning (ICML\u201920)","author":"Franceschi Jean-Yves","year":"2020","unstructured":"Jean-Yves Franceschi, Edouard Delasalles, Micka\u00ebl Chen, Sylvain Lamprier, and Patrick Gallinari. 2020. Stochastic latent residual video prediction. In Proceedings of the International Conference on Machine Learning (ICML\u201920). 3233\u20133246."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490586"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2883743"},{"key":"e_1_3_2_17_2","first-page":"2672","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201914)","author":"Goodfellow Ian J.","year":"2014","unstructured":"Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201914). 2672\u20132680."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639163"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_23_2","first-page":"1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence Workshop on Artificial Intelligence Safety (AAAIW\u201921)","author":"Hernandez-Ortega Javier","year":"2021","unstructured":"Javier Hernandez-Ortega, Rub\u00e9n Tolosana, Julian Fi\u00e9rrez, and Aythami Morales. 2021. Deepfakeson-phys: Deepfakes detection based on heart rate estimation. In Proceedings of the AAAI Conference on Artificial Intelligence Workshop on Artificial Intelligence Safety (AAAIW\u201921). 1\u20138."},{"key":"e_1_3_2_24_2","first-page":"1","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201915) Workshop","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeffrey Dean. 2015. Distilling the knowledge in a neural network. In Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS\u201915) Workshop. 1\u20139."},{"key":"e_1_3_2_25_2","article-title":"Adversarially robust deepfake media detection using fused convolutional neural network predictions","author":"Khan Sohail Ahmed","year":"2021","unstructured":"Sohail Ahmed Khan, Alessandro Artusi, and Hang Dai. 2021. Adversarially robust deepfake media detection using fused convolutional neural network predictions. arXiv:2102.05950. Retrieved from https:\/\/arxiv.org\/abs\/2102.05950.","journal-title":"arXiv:2102.05950"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00111"},{"key":"e_1_3_2_27_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201915)","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 (ICLR\u201915)."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"e_1_3_2_29_2","article-title":"Celeb-DF (v2): A new dataset for deepfake forensics","author":"Li Yuezun","year":"2019","unstructured":"Yuezun Li, Xin Yang, Pu Sun, Honggang Qi, and Siwei Lyu. 2019. Celeb-DF (v2): A new dataset for deepfake forensics. arXiv:1909.12962. Retrieved from https:\/\/arxiv.org\/abs\/1909.12962.","journal-title":"arXiv:1909.12962"},{"key":"e_1_3_2_30_2","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR\u201920)","author":"Liang Ruofan","year":"2020","unstructured":"Ruofan Liang, Tianlin Li, Longfei Li, Jing Wang, and Quanshi Zhang. 2020. Knowledge consistency between neural networks and beyond. In Proceedings of the International Conference on Learning Representations (ICLR\u201920)."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524497"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2019.00020"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3425780"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS46853.2019.9185974"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3093446"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_3_2_41_2","first-page":"80","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW\u201919)","author":"Sabir Ekraam","year":"2019","unstructured":"Ekraam Sabir, Jiaxin Cheng, Ayush Jaiswal, Wael AbdAlmageed, Iacopo Masi, and Prem Natarajan. 2019. Recurrent convolutional strategies for face manipulation detection in videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW\u201919). 80\u201387."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_43_2","article-title":"Learning video representations using contrastive bidirectional transformer","author":"Sun Chen","year":"2019","unstructured":"Chen Sun, Fabien Baradel, Kevin Murphy, and Cordelia Schmid. 2019. Learning video representations using contrastive bidirectional transformer. arXiv:1906.05743. Retrieved from https:\/\/arxiv.org\/abs\/1906.05743.","journal-title":"arXiv:1906.05743"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00361"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818056"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.014"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"issue":"86","key":"e_1_3_2_50_2","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten Laurens Van der","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 86 (2008), 2579\u20132605.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478324"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00089"},{"key":"e_1_3_2_53_2","article-title":"New theory cracks open the black box of deep learning","volume":"3","author":"Wolchover Natalie","year":"2017","unstructured":"Natalie Wolchover and Lucy Reading. 2017. New theory cracks open the black box of deep learning. Quanta Mag. 3 (2017).","journal-title":"Quanta Mag."},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW50321.2020.9096939"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/178"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00295"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413769"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3536426","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3536426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:50Z","timestamp":1750186970000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3536426"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,30]]},"references-count":58,"journal-issue":{"issue":"2s","published-print":{"date-parts":[[2022,6,30]]}},"alternative-id":["10.1145\/3536426"],"URL":"https:\/\/doi.org\/10.1145\/3536426","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,30]]},"assertion":[{"value":"2022-02-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-05-06","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}