{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T18:34:37Z","timestamp":1775846077920,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,12]]},"DOI":"10.1145\/3591106.3592218","type":"proceedings-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T22:33:38Z","timestamp":1686263618000},"page":"162-171","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["AVForensics: Audio-driven Deepfake Video Detection with Masking Strategy in Self-supervision"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3686-4420","authenticated-orcid":false,"given":"Yizhe","family":"Zhu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, China and CloudWalk Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8554-7827","authenticated-orcid":false,"given":"Jialin","family":"Gao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9943-5482","authenticated-orcid":false,"given":"Xi","family":"Zhou","sequence":"additional","affiliation":[{"name":"CloudWalk Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"e_1_3_2_1_2_1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in Neural Information Processing Systems 33 (2020), 12449\u201312460.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16193"},{"key":"e_1_3_2_1_5_1","volume-title":"Local Relation Learning for Face Forgery Detection. CoRR abs\/2105.02577","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. CoRR abs\/2105.02577 (2021)."},{"key":"e_1_3_2_1_6_1","volume-title":"International conference on machine learning. PMLR, 1597\u20131607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597\u20131607."},{"key":"e_1_3_2_1_7_1","volume-title":"Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297","author":"Chen Xinlei","year":"2020","unstructured":"Xinlei Chen, Haoqi Fan, Ross Girshick, and Kaiming He. 2020. Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"e_1_3_2_1_9_1","volume-title":"Voice-Face Homogeneity Tells Deepfake. arXiv preprint arXiv:2203.02195","author":"Cheng Harry","year":"2022","unstructured":"Harry Cheng, Yangyang Guo, Tianyi Wang, Qi Li, Tao Ye, and Liqiang Nie. 2022. Voice-Face Homogeneity Tells Deepfake. arXiv preprint arXiv:2203.02195 (2022)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463642"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"e_1_3_2_1_13_1","volume-title":"Voxceleb2: Deep speaker recognition. arXiv preprint arXiv:1806.05622","author":"Chung Joon\u00a0Son","year":"2018","unstructured":"Joon\u00a0Son Chung, Arsha Nagrani, and Andrew Zisserman. 2018. Voxceleb2: Deep speaker recognition. arXiv preprint arXiv:1806.05622 (2018)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06433-3_19"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00582"},{"key":"e_1_3_2_1_16_1","volume-title":"On the Detection of Digital Face Manipulation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 5780\u20135789","author":"Dang Hao","year":"2020","unstructured":"Hao Dang, Feng Liu, Joel Stehouwer, Xiaoming Liu, and Anil\u00a0K. Jain. 2020. On the Detection of Digital Face Manipulation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR. 5780\u20135789."},{"key":"e_1_3_2_1_17_1","volume-title":"Anti-forensics for face swapping videos via adversarial training","author":"Ding Feng","year":"2021","unstructured":"Feng Ding, Guopu Zhu, Yingcan Li, Xinpeng Zhang, Pradeep\u00a0K Atrey, and Siwei Lyu. 2021. Anti-forensics for face swapping videos via adversarial training. IEEE Transactions on Multimedia (2021)."},{"key":"e_1_3_2_1_18_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\u00a0Canton Ferrer. 2019. The deepfake detection challenge (dfdc) preview dataset. arXiv preprint arXiv:1910.08854 (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00925"},{"key":"e_1_3_2_1_20_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 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_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531350"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174136"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.324"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_26_1","volume-title":"Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems 33","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch\u00e9, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila\u00a0Pires, Zhaohan Guo, Mohammad Gheshlaghi\u00a0Azar, 2020. Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems 33 (2020), 21271\u201321284."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639163"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"e_1_3_2_1_30_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_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00808"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_18"},{"key":"e_1_3_2_1_37_1","volume-title":"Active contrastive learning of audio-visual video representations. arXiv preprint arXiv:2009.09805","author":"Ma Shuang","year":"2020","unstructured":"Shuang Ma, Zhaoyang Zeng, Daniel McDuff, and Yale Song. 2020. Active contrastive learning of audio-visual video representations. arXiv preprint arXiv:2009.09805 (2020)."},{"key":"e_1_3_2_1_38_1","volume-title":"Contrastive learning of global and local audio-visual representations. arXiv preprint arXiv:2104.05418","author":"Ma Shuang","year":"2021","unstructured":"Shuang Ma, Zhaoyang Zeng, Daniel McDuff, and Yale Song. 2021. Contrastive learning of global and local audio-visual representations. arXiv preprint arXiv:2104.05418 (2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS46853.2019.9185974"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"e_1_3_2_1_45_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van\u00a0den Oord Aaron","year":"2018","unstructured":"Aaron van\u00a0den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_46_1","volume-title":"Multi-modal self-supervision from generalized data transformations. arXiv preprint arXiv:2003.04298","author":"Patrick Mandela","year":"2020","unstructured":"Mandela Patrick, Yuki\u00a0M Asano, Polina Kuznetsova, Ruth Fong, Joao\u00a0F Henriques, Geoffrey Zweig, and Andrea Vedaldi. 2020. Multi-modal self-supervision from generalized data transformations. arXiv preprint arXiv:2003.04298 (2020)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01411"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_3_2_1_51_1","first-page":"80","article-title":"Recurrent convolutional strategies for face manipulation detection in videos","volume":"3","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. Interfaces (GUI) 3, 1 (2019), 80\u201387.","journal-title":"Interfaces (GUI)"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2018.01.010"},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 6447\u20136456","author":"Son\u00a0Chung Joon","year":"2017","unstructured":"Joon Son\u00a0Chung, Andrew Senior, Oriol Vinyals, and Andrew Zisserman. 2017. Lip reading sentences in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition. 6447\u20136456."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250518"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"e_1_3_2_1_56_1","volume-title":"International conference on machine learning. PMLR, 6105\u20136114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105\u20136114."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"e_1_3_2_1_60_1","volume-title":"Visualizing data using t-SNE.Journal of machine learning research 9, 11","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 (2008)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531415"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"e_1_3_2_1_63_1","volume-title":"Deepfake video detection using convolutional vision transformer. arXiv preprint arXiv:2102.11126","author":"Wodajo Deressa","year":"2021","unstructured":"Deressa Wodajo and Solomon Atnafu. 2021. Deepfake video detection using convolutional vision transformer. arXiv preprint arXiv:2102.11126 (2021)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390683"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Daichi Zhang Chenyu Li Fanzhao Lin Dan Zeng and Shiming Ge. 2021. Detecting Deepfake Videos with Temporal Dropout 3DCNN.. In IJCAI. 1288\u20131294.","DOI":"10.24963\/ijcai.2021\/178"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00148"}],"event":{"name":"ICMR '23: International Conference on Multimedia Retrieval","location":"Thessaloniki Greece","acronym":"ICMR '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2023 ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592218","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591106.3592218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:22Z","timestamp":1750182682000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592218"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":66,"alternative-id":["10.1145\/3591106.3592218","10.1145\/3591106"],"URL":"https:\/\/doi.org\/10.1145\/3591106.3592218","relation":{},"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}