{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T08:57:42Z","timestamp":1765357062898,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Plan","award":["2020AAA0140001"],"award-info":[{"award-number":["2020AAA0140001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1145\/3469877.3490586","type":"proceedings-article","created":{"date-parts":[[2022,1,10]],"date-time":"2022-01-10T18:27:21Z","timestamp":1641839241000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Latent Pattern Sensing: Deepfake Video Detection via Predictive Representation Learning"],"prefix":"10.1145","author":[{"given":"Shiming","family":"Ge","sequence":"first","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanzhao","family":"Lin","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyu","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daichi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyong","family":"Tan","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Engineering, Chinese Academy of Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Shanghai University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,1,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"D. Afchar V. Nozick J. Yamagishi and I. Echizen. 2018. MesoNet: A compact facial video forgery detection network. In BTAS. 1\u20137.  D. Afchar V. Nozick J. Yamagishi and I. Echizen. 2018. MesoNet: A compact facial video forgery detection network. In BTAS. 1\u20137.","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"R. Arandjelovic P. Gronat A. Torii T. Pajdla and J. Sivic. 2016. NetVLAD: CNN architecture for weakly supervised place recognition. In CVPR. 5297\u20135307.  R. Arandjelovic P. Gronat A. Torii T. Pajdla and J. Sivic. 2016. NetVLAD: CNN architecture for weakly supervised place recognition. In CVPR. 5297\u20135307.","DOI":"10.1109\/CVPR.2016.572"},{"key":"e_1_3_2_1_3_1","unstructured":"N. Ballas L. Yao C. Pal and A. Courville. 2016. Delving deeper into convolutional networks for learning video representations. In ICLR.  N. Ballas L. Yao C. Pal and A. Courville. 2016. Delving deeper into convolutional networks for learning video representations. In ICLR."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"C. Bregler M. Covell and M. Slaney. 1997. Video rewrite: Driving visual speech with audio. In SIGGRAPH. 353\u2013360.  C. Bregler M. Covell and M. Slaney. 1997. Video rewrite: Driving visual speech with audio. In SIGGRAPH. 353\u2013360.","DOI":"10.1145\/258734.258880"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/184656.180369"},{"key":"e_1_3_2_1_6_1","volume-title":"Towards solving the deepfake problem : An analysis on improving deepfake detection using dynamic face augmentation. arXiv:2102.09603","author":"Das S.","year":"2021","unstructured":"S. Das , S. Seferbekov , A. Datta , M. Islam , and M Amin . 2021. Towards solving the deepfake problem : An analysis on improving deepfake detection using dynamic face augmentation. arXiv:2102.09603 ( 2021 ). S. Das, S. Seferbekov, A. Datta, M. Islam, and M Amin. 2021. Towards solving the deepfake problem : An analysis on improving deepfake detection using dynamic face augmentation. arXiv:2102.09603 (2021)."},{"key":"e_1_3_2_1_7_1","unstructured":"E. Denton and V. Birodkar. 2017. Unsupervised learning of disentangled representations from video. In NeurIPS Vol.\u00a030. 1\u201310.  E. Denton and V. Birodkar. 2017. Unsupervised learning of disentangled representations from video. In NeurIPS Vol.\u00a030. 1\u201310."},{"key":"e_1_3_2_1_8_1","unstructured":"B. Dolhansky R. Howes B. Pflaum N. Baram and C. Canton-Ferrer. 2019. The deepfake detection challenge (DFDC) preview dataset. arXiv: 1910.08854 (2019).  B. Dolhansky R. Howes B. Pflaum N. Baram and C. Canton-Ferrer. 2019. The deepfake detection challenge (DFDC) preview dataset. arXiv: 1910.08854 (2019)."},{"key":"e_1_3_2_1_9_1","unstructured":"J. Franceschi E. Delasalles M. Chen S. Lamprier and P. Gallinari. 2020. Stochastic latent residual video prediction. In ICML. 3233\u20133246.  J. Franceschi E. Delasalles M. Chen S. Lamprier and P. Gallinari. 2020. Stochastic latent residual video prediction. In ICML. 3233\u20133246."},{"key":"e_1_3_2_1_10_1","unstructured":"I. Goodfellow J. Pouget-Abadie M. Mirza B. Xu D. Warde-Farley S. Ozair A. Courville and Y. Bengio. 2014. Generative adversarial nets. In NeurIPS. 2672\u20132680.  I. Goodfellow J. Pouget-Abadie M. Mirza B. Xu D. Warde-Farley S. Ozair A. Courville and Y. Bengio. 2014. Generative adversarial nets. In NeurIPS. 2672\u20132680."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"D. G\u00fcera and E. Delp. 2018. Deepfake video detection using recurrent neural networks. In AVSS. 1\u20136.  D. G\u00fcera and E. Delp. 2018. Deepfake video detection using recurrent neural networks. In AVSS. 1\u20136.","DOI":"10.1109\/AVSS.2018.8639163"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"A. Haliassos K. Vougioukas S. Petridis and M. Pantic. 2021. Lips don\u2019t lie: A generalisable and robust approach to face forgery detection. In CVPR. 5039\u20135049.  A. Haliassos K. Vougioukas S. Petridis and M. Pantic. 2021. Lips don\u2019t lie: A generalisable and robust approach to face forgery detection. In CVPR. 5039\u20135049.","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"T. Han W. Xie and A. Zisserman. 2019. Video representation learning by dense predictive coding. In ICCVW. 1\u201310.  T. Han W. Xie and A. Zisserman. 2019. Video representation learning by dense predictive coding. In ICCVW. 1\u201310.","DOI":"10.1109\/ICCVW.2019.00186"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"T. Han W. Xie and A. Zisserman. 2020. Memory-Augmented Dense Predictive Coding for Video Representation Learning. In ECCV. 312\u2013329.  T. Han W. Xie and A. Zisserman. 2020. Memory-Augmented Dense Predictive Coding for Video Representation Learning. In ECCV. 312\u2013329.","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"J. Hernandez-Ortega R. Tolosana J. Fi\u00e9rrez and A. Morales. 2021. DeepFakesON-Phys: Deepfakes detection based on heart rate estimation. In AAAIW Vol.\u00a02808.  J. Hernandez-Ortega R. Tolosana J. Fi\u00e9rrez and A. Morales. 2021. DeepFakesON-Phys: Deepfakes detection based on heart rate estimation. In AAAIW Vol.\u00a02808.","DOI":"10.1007\/978-3-030-87664-7_12"},{"key":"e_1_3_2_1_16_1","unstructured":"S. Khan A. Artusi and H. Dai. 2021. Adversarially robust deepfake media detection using fused convolutional neural network predictions. arXiv:2102.05950 (2021).  S. Khan A. Artusi and H. Dai. 2021. Adversarially robust deepfake media detection using fused convolutional neural network predictions. arXiv:2102.05950 (2021)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"M. Kim S. Tariq and S. Woo. 2021. FReTAL: Generalizing deepfake detection using knowledge distillation and representation learning. In CVPRW. 1001\u20131012.  M. Kim S. Tariq and S. Woo. 2021. FReTAL: Generalizing deepfake detection using knowledge distillation and representation learning. In CVPRW. 1001\u20131012.","DOI":"10.1109\/CVPRW53098.2021.00111"},{"key":"e_1_3_2_1_18_1","volume-title":"Adam: A method for stochastic optimization. In ICLR.","author":"Kingma D.","year":"2015","unstructured":"D. Kingma and J. Ba . 2015 . Adam: A method for stochastic optimization. In ICLR. D. Kingma and J. Ba. 2015. Adam: A method for stochastic optimization. In ICLR."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"L. Li J. Bao H. Yang D. Chen and F. Wen. 2020. Advancing high fidelity identity swapping for forgery detection. In CVPR. 5074\u20135083.  L. Li J. Bao H. Yang D. Chen and F. Wen. 2020. Advancing high fidelity identity swapping for forgery detection. In CVPR. 5074\u20135083.","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"e_1_3_2_1_20_1","unstructured":"Y. Li X. Yang P. Sun H. Qi and S. Lyu. 2019. Celeb-DF (v2): A new dataset for deepfake forensics. arXiv:1909.12962 (2019).  Y. Li X. Yang P. Sun H. Qi and S. Lyu. 2019. Celeb-DF (v2): A new dataset for deepfake forensics. arXiv:1909.12962 (2019)."},{"key":"e_1_3_2_1_21_1","unstructured":"R Liang T. Li L. Li J. Wang and Q. Zhang. 2020. Knowledge consistency between neural networks and beyond. In ICLR.  R Liang T. Li L. Li J. Wang and Q. Zhang. 2020. Knowledge consistency between neural networks and beyond. In ICLR."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"H. Liu X. Li W. Zhou Y. Chen Y. He H. Xue W. Zhang and N. Yu. 2021. Spatial-phase shallow learning: rethinking face forgery detection in frequency domain. In CVPR. 772\u2013781.  H. Liu X. Li W. Zhou Y. Chen Y. He H. Xue W. Zhang and N. Yu. 2021. Spatial-phase shallow learning: rethinking face forgery detection in frequency domain. In CVPR. 772\u2013781.","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"e_1_3_2_1_23_1","unstructured":"W Lotter G. Kreiman and D. Cox. 2017. Deep predictive coding networks for video prediction and unsupervised learning. In ICLR.  W Lotter G. Kreiman and D. Cox. 2017. Deep predictive coding networks for video prediction and unsupervised learning. In ICLR."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Y. Luo Y. Zhang J. Yan and W. Liu. 2021. Generalizing face forgery detection with high-frequency features. In CVPR. 16317\u201316326.  Y. Luo Y. Zhang J. Yan and W. Liu. 2021. Generalizing face forgery detection with high-frequency features. In CVPR. 16317\u201316326.","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"F. Matern C. Riess and M. Stamminger. 2019. Exploiting visual artifacts to expose deepfakes and face manipulations. In WACVW. 83\u201392.  F. Matern C. Riess and M. Stamminger. 2019. Exploiting visual artifacts to expose deepfakes and face manipulations. In WACVW. 83\u201392.","DOI":"10.1109\/WACVW.2019.00020"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"T. Mittal U. Bhattacharya R. Chandra A. Bera and D. Manocha. 2020. Emotions don\u2019t lie: An audio-visual deepfake detection method using affective cues. In ACM Multimedia. 2823\u20132832.  T. Mittal U. Bhattacharya R. Chandra A. Bera and D. Manocha. 2020. Emotions don\u2019t lie: An audio-visual deepfake detection method using affective cues. In ACM Multimedia. 2823\u20132832.","DOI":"10.1145\/3394171.3413570"},{"volume-title":"International Conference on Biometrics Theory, Applications and Systems. 1\u20138.","author":"Nguyen H.","key":"e_1_3_2_1_27_1","unstructured":"H. Nguyen , F. Fang , J. Yamagishi , and I. Echizen . 2019. Multi-task learning for detecting and segmenting manipulated facial images and videos . In International Conference on Biometrics Theory, Applications and Systems. 1\u20138. H. Nguyen, F. Fang, J. Yamagishi, and I. Echizen. 2019. Multi-task learning for detecting and segmenting manipulated facial images and videos. In International Conference on Biometrics Theory, Applications and Systems. 1\u20138."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"O.\u00a0M. Parkhi A. Vedaldi and A. Zisserman. 2015. Deep face recognition. In BMVC. Article 41 12\u00a0pages.  O.\u00a0M. Parkhi A. Vedaldi and A. Zisserman. 2015. Deep face recognition. In BMVC. Article 41 12\u00a0pages.","DOI":"10.5244\/C.29.41"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"A. Rossler D. Cozzolino L. Verdoliva C. Riess J. Thies and M. Nie\u00dfner. 2019. FaceForensics++: Learning to detect manipulated facial images. In ICCV. 1\u201311.  A. Rossler D. Cozzolino L. Verdoliva C. Riess J. Thies and M. Nie\u00dfner. 2019. FaceForensics++: Learning to detect manipulated facial images. In ICCV. 1\u201311.","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_3_2_1_30_1","unstructured":"E. Sabir J. Cheng A. Jaiswal W. Abd I. Masi and P. Natarajan. 2019. Recurrent convolutional strategies for face manipulation detection in videos. In ICCVW. 80\u201387.  E. Sabir J. Cheng A. Jaiswal W. Abd I. Masi and P. Natarajan. 2019. Recurrent convolutional strategies for face manipulation detection in videos. In ICCVW. 80\u201387."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"F. Schroff D. Kalenichenko and J. Philbin. 2015. FaceNet: A unified embedding for face recognition and clustering. In CVPR. 815\u2013823.  F. Schroff D. Kalenichenko and J. Philbin. 2015. FaceNet: A unified embedding for face recognition and clustering. In CVPR. 815\u2013823.","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_32_1","unstructured":"C. Sun F. Baradel K. Murphy and C. Schmid. 2019. Learning video representations using contrastive bidirectional transformer. arXiv:1906.05743 (2019).  C. Sun F. Baradel K. Murphy and C. Schmid. 2019. Learning video representations using contrastive bidirectional transformer. arXiv:1906.05743 (2019)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Z. Sun Y. Han Z. Hua N. Ruan and W. Jia. 2021. Improving the efficiency and robustness of deepfakes detection through precise geometric features. In CVPR. 3609\u20133618.  Z. Sun Y. Han Z. Hua N. Ruan and W. Jia. 2021. Improving the efficiency and robustness of deepfakes detection through precise geometric features. In CVPR. 3609\u20133618.","DOI":"10.1109\/CVPR46437.2021.00361"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818056"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"J. Thies M. Zollhofer M. Stamminger C. Theobalt and M. Nie\u00dfner. 2016. Face2face: Real-time face capture and reenactment of rgb videos. In ICCV. 2387\u20132395.  J. Thies M. Zollhofer M. Stamminger C. Theobalt and M. Nie\u00dfner. 2016. Face2face: Real-time face capture and reenactment of rgb videos. In ICCV. 2387\u20132395.","DOI":"10.1109\/CVPR.2016.262"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.014"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"S. Tulyakov M. Liu X. Yang and J. Kautz. 2018. MoCoGAN: Decomposing motion and content for video generation. In ICCV. 1526\u20131535.  S. Tulyakov M. Liu X. Yang and J. Kautz. 2018. MoCoGAN: Decomposing motion and content for video generation. In ICCV. 1526\u20131535.","DOI":"10.1109\/CVPR.2018.00165"},{"key":"e_1_3_2_1_39_1","first-page":"11","article-title":"2008. Visualizing data using t-SNE","volume":"9","author":"Van\u00a0der Maaten L.","year":"2008","unstructured":"L. Van\u00a0der Maaten and G. Hinton . 2008. Visualizing data using t-SNE . Journal of Machine Learning Research 9 , 11 ( 2008 ), 2579\u20132605. L. Van\u00a0der Maaten and G. Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 11 (2008), 2579\u20132605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"J. Wang Y. Liu Y. Hu H. Shi and T. Mei. 2021. FaceX-Zoo: A pytorch toolbox for face recognition. arXiv:2101.04407 (2021).  J. Wang Y. Liu Y. Hu H. Shi and T. Mei. 2021. FaceX-Zoo: A pytorch toolbox for face recognition. arXiv:2101.04407 (2021).","DOI":"10.1145\/3474085.3478324"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Y. Wang and Antitza D.2020. A video is worth more than 1000 lies. Comparing 3DCNN approaches for detecting deepfakes. In FG. 515\u2013519.  Y. Wang and Antitza D.2020. A video is worth more than 1000 lies. Comparing 3DCNN approaches for detecting deepfakes. In FG. 515\u2013519.","DOI":"10.1109\/FG47880.2020.00089"},{"key":"e_1_3_2_1_42_1","unstructured":"N. Wolchover and L. Reading. 2017. New theory cracks open the black box of deep learning. Quanta Magazine 3(2017).  N. Wolchover and L. Reading. 2017. New theory cracks open the black box of deep learning. Quanta Magazine 3(2017)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"C. Yeh H. Chen S. Tsai and S. Wang. 2020. Disrupting image-translation-based deepfake algorithms with adversarial attacks. In WACVW. 53\u201362.  C. Yeh H. Chen S. Tsai and S. Wang. 2020. Disrupting image-translation-based deepfake algorithms with adversarial attacks. In WACVW. 53\u201362.","DOI":"10.1109\/WACVW50321.2020.9096939"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"D. Zhang C. Li F. Lin D. Zeng and S. Ge. 2021. Detecting deepfake videos with temporal dropout 3DCNN. In IJCAI. 565\u2013573.  D. Zhang C. Li F. Lin D. Zeng and S. Ge. 2021. Detecting deepfake videos with temporal dropout 3DCNN. In IJCAI. 565\u2013573.","DOI":"10.24963\/ijcai.2021\/178"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"H. Zhao W. Zhou D. Chen T. Wei W. Zhang and N. Yu. 2021. Multi-attentional deepfake detection. In CVPR. 2185\u20132194.  H. Zhao W. Zhou D. Chen T. Wei W. Zhang and N. Yu. 2021. Multi-attentional deepfake detection. In CVPR. 2185\u20132194.","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"X. Zhu H. Wang H. Fei Z. Lei and S. Li. 2021. Face forgery detection by 3d decomposition. In CVPR. 2929\u20132939.  X. Zhu H. Wang H. Fei Z. Lei and S. Li. 2021. Face forgery detection by 3d decomposition. In CVPR. 2929\u20132939.","DOI":"10.1109\/CVPR46437.2021.00295"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413769"}],"event":{"name":"MMAsia '21: ACM Multimedia Asia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Gold Coast Australia","acronym":"MMAsia '21"},"container-title":["ACM Multimedia Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469877.3490586","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3469877.3490586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:16Z","timestamp":1750188616000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3469877.3490586"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":47,"alternative-id":["10.1145\/3469877.3490586","10.1145\/3469877"],"URL":"https:\/\/doi.org\/10.1145\/3469877.3490586","relation":{},"subject":[],"published":{"date-parts":[[2021,12]]},"assertion":[{"value":"2022-01-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}