{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T03:46:11Z","timestamp":1784000771181,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["No. 2019YFC1521104"],"award-info":[{"award-number":["No. 2019YFC1521104"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972157"],"award-info":[{"award-number":["61972157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]},{"name":"Zhejiang Lab","award":["2020NB0AB01"],"award-info":[{"award-number":["2020NB0AB01"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475508","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T06:09:05Z","timestamp":1634537345000},"page":"3473-3481","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":158,"title":["Spatiotemporal Inconsistency Learning for DeepFake Video Detection"],"prefix":"10.1145","author":[{"given":"Zhihao","family":"Gu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taiping","family":"Yao","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shouhong","family":"Ding","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilin","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feiyue","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_1_2_1","volume-title":"Local Relation Learning for Face Forgery Detection. In Thirty-Fifth AAAI Conference on Artificial Intelligence. AAAI Press, 1081--1088","author":"Chen Shen","year":"2021","unstructured":"Shen Chen , Taiping Yao , Yang Chen , Shouhong Ding , Jilin Li , and Rongrong Ji . 2021 . Local Relation Learning for Face Forgery Detection. In Thirty-Fifth AAAI Conference on Artificial Intelligence. AAAI Press, 1081--1088 . Shen Chen, Taiping Yao, Yang Chen, Shouhong Ding, Jilin Li, and Rongrong Ji. 2021. Local Relation Learning for Face Forgery Detection. In Thirty-Fifth AAAI Conference on Artificial Intelligence. AAAI Press, 1081--1088."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070781.2024164"},{"key":"e_1_3_2_1_4_1","volume-title":"On the Detection of Digital Face Manipulation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 5780--5789","author":"Dang Hao","unstructured":"Hao Dang , Feng Liu , Joel Stehouwer , Xiaoming Liu , and Anil K. Jain . 2020 . On the Detection of Digital Face Manipulation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 5780--5789 . Hao Dang, Feng Liu, Joel Stehouwer, Xiaoming Liu, and Anil K. Jain. 2020. On the Detection of Digital Face Manipulation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 5780--5789."},{"key":"e_1_3_2_1_5_1","volume-title":"The Deepfake Detection Challenge (DFDC) Preview Dataset. CoRR","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. CoRR , Vol. abs\/ 1910 .08854 ( 2019 ). Brian Dolhansky, Russ Howes, Ben Pflaum, Nicole Baram, and Cristian Canton-Ferrer. 2019. The Deepfake Detection Challenge (DFDC) Preview Dataset. CoRR, Vol. abs\/1910.08854 (2019)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2190402"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.537"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413732"},{"key":"e_1_3_2_1_10_1","volume-title":"Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations.","author":"Diederik","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015 . Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations."},{"key":"e_1_3_2_1_11_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 ). 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_12_1","volume-title":"Face X-Ray for More General Face Forgery Detection. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 5000--5009","author":"Li Lingzhi","year":"2020","unstructured":"Lingzhi Li , Jianmin Bao , Ting Zhang , Hao Yang , Dong Chen , Fang Wen , and Baining Guo . 2020 a . Face X-Ray for More General Face Forgery Detection. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 5000--5009 . Lingzhi Li, Jianmin Bao, Ting Zhang, Hao Yang, Dong Chen, Fang Wen, and Baining Guo. 2020 a. Face X-Ray for More General Face Forgery Detection. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 5000--5009."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414034"},{"key":"e_1_3_2_1_14_1","volume-title":"Exposing DeepFake Videos By Detecting Face Warping Artifacts. In IEEE Conference on Computer Vision and Pattern Recognition Workshops. Computer Vision Foundation \/ IEEE, 46--52","author":"Li Yuezun","year":"2019","unstructured":"Yuezun Li and Siwei Lyu . 2019 . Exposing DeepFake Videos By Detecting Face Warping Artifacts. In IEEE Conference on Computer Vision and Pattern Recognition Workshops. Computer Vision Foundation \/ IEEE, 46--52 . Yuezun Li and Siwei Lyu. 2019. Exposing DeepFake Videos By Detecting Face Warping Artifacts. In IEEE Conference on Computer Vision and Pattern Recognition Workshops. Computer Vision Foundation \/ IEEE, 46--52."},{"key":"e_1_3_2_1_15_1","volume-title":"Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 3204--3213","author":"Li Yuezun","year":"2020","unstructured":"Yuezun Li , Xin Yang , Pu Sun , Honggang Qi , and Siwei Lyu . 2020 c . Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 3204--3213 . Yuezun Li, Xin Yang, Pu Sun, Honggang Qi, and Siwei Lyu. 2020 c. Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 3204--3213."},{"key":"e_1_3_2_1_16_1","volume-title":"TSM: Temporal Shift Module for Efficient Video Understanding. In 2019 IEEE\/CVF International Conference on Computer Vision. IEEE, 7082--7092","author":"Lin Ji","year":"2019","unstructured":"Ji Lin , Chuang Gan , and Song Han . 2019 . TSM: Temporal Shift Module for Efficient Video Understanding. In 2019 IEEE\/CVF International Conference on Computer Vision. IEEE, 7082--7092 . Ji Lin, Chuang Gan, and Song Han. 2019. TSM: Temporal Shift Module for Efficient Video Understanding. In 2019 IEEE\/CVF International Conference on Computer Vision. IEEE, 7082--7092."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"e_1_3_2_1_18_1","volume-title":"Shenoy Pratik Gurudatt","author":"Masi Iacopo","year":"2020","unstructured":"Iacopo Masi , Aditya Killekar , Royston Marian Mascarenhas , Shenoy Pratik Gurudatt , and Wael AbdAlmageed. 2020 . Two-Branch Recurrent Network for Isolating Deepfakes in Videos. In Computer Vision - ECCV 2020 - 16th European Conference, Vol. 12352 . Springer , 667--684. Iacopo Masi, Aditya Killekar, Royston Marian Mascarenhas, Shenoy Pratik Gurudatt, and Wael AbdAlmageed. 2020. Two-Branch Recurrent Network for Isolating Deepfakes in Videos. In Computer Vision - ECCV 2020 - 16th European Conference, Vol. 12352. Springer, 667--684."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2019.00020"},{"key":"e_1_3_2_1_20_1","volume-title":"Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos. In 10th IEEE International Conference on Biometrics Theory, Applications and Systems. IEEE, 1--8.","author":"Nguyen Huy H.","year":"2019","unstructured":"Huy H. Nguyen , Fuming Fang , Junichi Yamagishi , and Isao Echizen . 2019 a . Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos. In 10th IEEE International Conference on Biometrics Theory, Applications and Systems. IEEE, 1--8. Huy H. Nguyen, Fuming Fang, Junichi Yamagishi, and Isao Echizen. 2019 a. Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos. In 10th IEEE International Conference on Biometrics Theory, Applications and Systems. IEEE, 1--8."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPhot.2012.6215223"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413707"},{"key":"e_1_3_2_1_24_1","volume-title":"Computer Vision - ECCV 2020 - 16th European Conference","author":"Qian Yuyang","unstructured":"Yuyang Qian , Guojun Yin , Lu Sheng , Zixuan Chen , and Jing Shao . 2020. Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues . In Computer Vision - ECCV 2020 - 16th European Conference , Vol. 12357 . Springer , 86--103. Yuyang Qian, Guojun Yin, Lu Sheng, Zixuan Chen, and Jing Shao. 2020. Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues. In Computer Vision - ECCV 2020 - 16th European Conference, Vol. 12357. Springer, 86--103."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_26_1","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision. IEEE, 1--11","author":"Andreas R\u00f6","year":"2019","unstructured":"Andreas R\u00f6 ssler, Davide Cozzolino , Luisa Verdoliva , Christian Riess , Justus Thies , and Matthias Nie\u00dfner . 2019 . FaceForensics: Learning to Detect Manipulated Facial Images . In 2019 IEEE\/CVF International Conference on Computer Vision. IEEE, 1--11 . Andreas R\u00f6 ssler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Nie\u00dfner. 2019. FaceForensics: Learning to Detect Manipulated Facial Images. In 2019 IEEE\/CVF International Conference on Computer Vision. IEEE, 1--11."},{"key":"e_1_3_2_1_27_1","volume-title":"Recurrent Convolutional Strategies for Face Manipulation Detection in Videos. In IEEE Conference on Computer Vision and Pattern Recognition Workshops. Computer Vision Foundation \/ IEEE, 80--87","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 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Computer Vision Foundation \/ IEEE, 80--87 . Ekraam Sabir, Jiaxin Cheng, Ayush Jaiswal, Wael AbdAlmageed, Iacopo Masi, and Prem Natarajan. 2019. Recurrent Convolutional Strategies for Face Manipulation Detection in Videos. In IEEE Conference on Computer Vision and Pattern Recognition Workshops. Computer Vision Foundation \/ IEEE, 80--87."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363269"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"e_1_3_2_1_31_1","volume-title":"C3D: Generic Features for Video Analysis. CoRR","author":"Tran Du","year":"2014","unstructured":"Du Tran , Lubomir D. Bourdev , Rob Fergus , Lorenzo Torresani , and Manohar Paluri . 2014. C3D: Generic Features for Video Analysis. CoRR , Vol. abs\/ 1412 .0767 ( 2014 ). Du Tran, Lubomir D. Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. 2014. C3D: Generic Features for Video Analysis. CoRR, Vol. abs\/1412.0767 (2014)."},{"key":"e_1_3_2_1_32_1","volume-title":"2020 c. Exposing Deep-faked Videos by Anomalous Co-motion Pattern Detection. CoRR","author":"Wang Gengxing","year":"2020","unstructured":"Gengxing Wang , Jiahuan Zhou , and Ying Wu . 2020 c. Exposing Deep-faked Videos by Anomalous Co-motion Pattern Detection. CoRR , Vol. abs\/ 2008 .04848 ( 2020 ). Gengxing Wang, Jiahuan Zhou, and Ying Wu. 2020 c. Exposing Deep-faked Videos by Anomalous Co-motion Pattern Detection. CoRR, Vol. abs\/2008.04848 (2020)."},{"key":"e_1_3_2_1_33_1","volume-title":"2020 a. TDN: Temporal Difference Networks for Efficient Action Recognition. CoRR","author":"Wang Limin","year":"2020","unstructured":"Limin Wang , Zhan Tong , Bin Ji , and Gangshan Wu . 2020 a. TDN: Temporal Difference Networks for Efficient Action Recognition. CoRR , Vol. abs\/ 2012 .10071 ( 2020 ). Limin Wang, Zhan Tong, Bin Ji, and Gangshan Wu. 2020 a. TDN: Temporal Difference Networks for Efficient Action Recognition. CoRR, Vol. abs\/2012.10071 (2020)."},{"key":"e_1_3_2_1_34_1","volume-title":"ICONIP 2020, Bangkok, Thailand, November 23-27, 2020, Proceedings, Part I (Lecture Notes in Computer Science","volume":"324","author":"Wang Xinyao","year":"2020","unstructured":"Xinyao Wang , Taiping Yao , Shouhong Ding , and Lizhuang Ma . 2020 b. Face Manipulation Detection via Auxiliary Supervision. In Neural Information Processing - 27th International Conference , ICONIP 2020, Bangkok, Thailand, November 23-27, 2020, Proceedings, Part I (Lecture Notes in Computer Science , Vol. 12532). Springer, 313-- 324 . Xinyao Wang, Taiping Yao, Shouhong Ding, and Lizhuang Ma. 2020 b. Face Manipulation Detection via Auxiliary Supervision. In Neural Information Processing - 27th International Conference, ICONIP 2020, Bangkok, Thailand, November 23-27, 2020, Proceedings, Part I (Lecture Notes in Computer Science, Vol. 12532). Springer, 313--324."},{"key":"e_1_3_2_1_35_1","volume-title":"Exposing Deep Fakes Using Inconsistent Head Poses. In IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 8261--8265","author":"Yang Xin","year":"2019","unstructured":"Xin Yang , Yuezun Li , and Siwei Lyu . 2019 . Exposing Deep Fakes Using Inconsistent Head Poses. In IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 8261--8265 . Xin Yang, Yuezun Li, and Siwei Lyu. 2019. Exposing Deep Fakes Using Inconsistent Head Poses. In IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE, 8261--8265."},{"key":"e_1_3_2_1_36_1","volume-title":"Multi-attentional Deepfake Detection. CoRR","author":"Zhao Hanqing","year":"2021","unstructured":"Hanqing Zhao , Wenbo Zhou , Dongdong Chen , Tianyi Wei , Weiming Zhang , and Nenghai Yu. 2021. Multi-attentional Deepfake Detection. CoRR , Vol. abs\/ 2103 .02406 ( 2021 ). Hanqing Zhao, Wenbo Zhou, Dongdong Chen, Tianyi Wei, Weiming Zhang, and Nenghai Yu. 2021. Multi-attentional Deepfake Detection. CoRR, Vol. abs\/2103.02406 (2021)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413769"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475508","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:09Z","timestamp":1750193349000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475508"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":37,"alternative-id":["10.1145\/3474085.3475508","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475508","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}