{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:24:30Z","timestamp":1759332270817,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["WK3480000011"],"award-info":[{"award-number":["WK3480000011"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Nature Science Foundation of China","award":["62121002, U1936210, 62232006, 62032006, 62102127"],"award-info":[{"award-number":["62121002, U1936210, 62232006, 62032006, 62102127"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612215","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"6907-6917","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["High Fidelity Face Swapping via Semantics Disentanglement and Structure Enhancement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4044-214X","authenticated-orcid":false,"given":"Fengyuan","family":"Liu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6403-761X","authenticated-orcid":false,"given":"Lingyun","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-5315","authenticated-orcid":false,"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2840-6235","authenticated-orcid":false,"given":"Chuanbin","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9591-8601","authenticated-orcid":false,"given":"Zhiguo","family":"Ding","sequence":"additional","affiliation":[{"name":"Third Research Institute of the Ministry of Public Security, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3997-0031","authenticated-orcid":false,"given":"Quanwei","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1151-1792","authenticated-orcid":false,"given":"Yongdong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2016. FaceSwap. https:\/\/github.com\/MarekKowalski\/FaceSwap."},{"key":"e_1_3_2_1_2_1","unstructured":"2017. DeepFakes. https:\/\/github.com\/deepfakes\/faceswap."},{"key":"e_1_3_2_1_3_1","unstructured":"2018. faceswap-GAN: A denoising autoencoder + adversarial losses and attention mechanisms for face swapping. https:\/\/github.com\/shaoanlu\/faceswap-GAN."},{"key":"e_1_3_2_1_4_1","volume-title":"Deep Variational Information Bottleneck. In 5th International Conference on Learning Representations.","author":"Alemi Alexander A.","year":"2017","unstructured":"Alexander A. Alemi, Ian Fischer, Joshua V. Dillon, and Kevin Murphy. 2017. Deep Variational Information Bottleneck. In 5th International Conference on Learning Representations."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVMP.2009.29"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2004.00799.x"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089909"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413630"},{"key":"e_1_3_2_1_10_1","volume-title":"19th Annual Conference of the International Speech Communication Association. 1086--1090","author":"Chung Joon Son","year":"2018","unstructured":"Joon Son Chung, Arsha Nagrani, and Andrew Zisserman. 2018. VoxCeleb2: Deep Speaker Recognition. In Interspeech 2018, 19th Annual Conference of the International Speech Communication Association. 1086--1090."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087709"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"e_1_3_2_1_13_1","volume-title":"What makes you, you? Analyzing Recognition by Swapping Face Parts. 26TH International Conference on Pattern Recognition","author":"Ferrari Claudio","year":"2022","unstructured":"Claudio Ferrari, Matteo Serpentoni, Stefano Berretti, and Alberto Del Bimbo. 2022. What makes you, you? Analyzing Recognition by Swapping Face Parts. 26TH International Conference on Pattern Recognition (2022)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00341"},{"key":"e_1_3_2_1_15_1","volume-title":"Generative Adversarial Nets. In Annual Conference on Neural Information Processing Systems. 2672--2680","author":"Goodfellow Ian J.","year":"2014","unstructured":"Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Annual Conference on Neural Information Processing Systems. 2672--2680."},{"volume-title":"European Conference on Computer Vision. 152--168","author":"Guo Jianzhu","key":"e_1_3_2_1_16_1","unstructured":"Jianzhu Guo, Xiangyu Zhu, Yang Yang, Fan Yang, Zhen Lei, and Stan Z. Li. 2020. Towards Fast, Accurate and Stable 3D Dense Face Alignment. In European Conference on Computer Vision. 152--168."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501814"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_1_19_1","volume-title":"6th International Conference on Learning Representations.","author":"Karras Tero","year":"2018","unstructured":"Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2018. Progressive Growing of GANs for Improved Quality, Stability, and Variation. In 6th International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"e_1_3_2_1_21_1","volume-title":"Analyzing and Improving the Image Quality of StyleGAN. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8107--8116","author":"Karras Tero","year":"2020","unstructured":"Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2020. Analyzing and Improving the Image Quality of StyleGAN. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8107--8116."},{"key":"e_1_3_2_1_22_1","volume-title":"Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10769--10778","author":"Kim Jiseob","year":"2022","unstructured":"Jiseob Kim, Jihoon Lee, and Byoung-Tak Zhang. 2022. Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10769--10778."},{"key":"e_1_3_2_1_23_1","volume-title":"Discriminative Feature Mining Based on Frequency Information and Metric Learning for Face Forgery Detection","author":"Li Jiaming","year":"2021","unstructured":"Jiaming Li, Hongtao Xie, Lingyun Yu, Xingyu Gao, and Yongdong Zhang. 2021. Discriminative Feature Mining Based on Frequency Information and Metric Learning for Face Forgery Detection. IEEE Transactions on Knowledge and Data Engineering (2021), 1--1."},{"key":"e_1_3_2_1_24_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_25_1","volume-title":"MomentDiff: Generative Video Moment Retrieval from Random to Real. arXiv preprint arXiv:2307.02869","author":"Li Pandeng","year":"2023","unstructured":"Pandeng Li, Chen-Wei Xie, Hongtao Xie, Liming Zhao, Lei Zhang, Yun Zheng, Deli Zhao, and Yongdong Zhang. 2023. MomentDiff: Generative Video Moment Retrieval from Random to Real. arXiv preprint arXiv:2307.02869 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Learning Disentangled Representation for One-shot Progressive Face Swapping. arXiv preprint arXiv:2203.12985","author":"Li Qi","year":"2022","unstructured":"Qi Li, Weining Wang, Chengzhong Xu, and Zhenan Sun. 2022. Learning Disentangled Representation for One-shot Progressive Face Swapping. arXiv preprint arXiv:2203.12985 (2022)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00013"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2012.26"},{"key":"e_1_3_2_1_29_1","volume-title":"Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784","author":"Mirza Mehdi","year":"2014","unstructured":"Mehdi Mirza and Simon Osindero. 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14062"},{"key":"e_1_3_2_1_31_1","volume-title":"Semantic Image Synthesis With Spatially-Adaptive Normalization. In IEEE Conference on Computer Vision and Pattern Recognition. 2337--2346","author":"Park Taesung","year":"2019","unstructured":"Taesung Park, Ming-Yu Liu, Ting-Chun Wang, and Jun-Yan Zhu. 2019. Semantic Image Synthesis With Spatially-Adaptive Normalization. In IEEE Conference on Computer Vision and Pattern Recognition. 2337--2346."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"volume-title":"Fine-Grained Head Pose Estimation Without Keypoints. In 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2074--2083","author":"Ruiz Nataniel","key":"e_1_3_2_1_33_1","unstructured":"Nataniel Ruiz, Eunji Chong, and James M. Rehg. 2018. Fine-Grained Head Pose Estimation Without Keypoints. In 2018 IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2074--2083."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580512"},{"key":"e_1_3_2_1_35_1","volume-title":"PRRNet: Pixel-Region Relation Network for Face Forgery Detection. Pattern Recogn","author":"Shang Zhihua","year":"2021","unstructured":"Zhihua Shang, Hongtao Xie, Zhengjun Zha, Lingyun Yu, Yan Li, and Yongdong Zhang. 2021. PRRNet: Pixel-Region Relation Network for Face Forgery Detection. Pattern Recogn., Vol. 116, C (aug 2021), 10 pages."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00767"},{"key":"e_1_3_2_1_37_1","volume-title":"CosFace: Large Margin Cosine Loss for Deep Face Recognition. In 2018 IEEE Conference on Computer Vision and Pattern Recognition. 5265--5274","author":"Wang Hao","year":"2018","unstructured":"Hao Wang, Yitong Wang, Zheng Zhou, Xing Ji, Dihong Gong, Jingchao Zhou, Zhifeng Li, and Wei Liu. 2018b. CosFace: Large Margin Cosine Loss for Deep Face Recognition. In 2018 IEEE Conference on Computer Vision and Pattern Recognition. 5265--5274."},{"key":"e_1_3_2_1_38_1","volume-title":"High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs. In 2018 IEEE Conference on Computer Vision and Pattern Recognition. 8798--8807","author":"Wang Ting-Chun","year":"2018","unstructured":"Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. 2018a. High-Resolution Image Synthesis and Semantic Manipulation With Conditional GANs. In 2018 IEEE Conference on Computer Vision and Pattern Recognition. 8798--8807."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/157"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Erroll Wood Tadas Baltrusaitis Charlie Hewitt Matthew Johnson Jingjing Shen Nikola Milosavljevic Daniel Wilde Stephan Garbin Toby Sharp Ivan Stojiljkovic et al. 2022. 3D face reconstruction with dense landmarks. arXiv preprint arXiv:2204.02776 (2022).","DOI":"10.1007\/978-3-031-19778-9_10"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00748"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00749"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16417"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091863"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"e_1_3_2_1_46_1","volume-title":"SEAN: Image Synthesis With Semantic Region-Adaptive Normalization. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5103--5112","author":"Zhu Peihao","year":"2020","unstructured":"Peihao Zhu, Rameen Abdal, Yipeng Qin, and Peter Wonka. 2020. SEAN: Image Synthesis With Semantic Region-Adaptive Normalization. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 5103--5112."},{"key":"e_1_3_2_1_47_1","volume-title":"One Shot Face Swapping on Megapixels. In IEEE Conference on Computer Vision and Pattern Recognition. 4834--4844","author":"Zhu Yuhao","year":"2021","unstructured":"Yuhao Zhu, Qi Li, Jian Wang, Cheng-Zhong Xu, and Zhenan Sun. 2021. One Shot Face Swapping on Megapixels. In IEEE Conference on Computer Vision and Pattern Recognition. 4834--4844."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612215","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:08:18Z","timestamp":1755821298000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612215"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":47,"alternative-id":["10.1145\/3581783.3612215","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612215","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}