{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:01:11Z","timestamp":1783530071153,"version":"3.55.0"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00938","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10064-10074","source":"Crossref","is-referenced-by-count":4,"title":["Canonswap: High-Fidelity and Consistent Video Face Swapping Via Canonical Space Modulation"],"prefix":"10.1109","author":[{"given":"Xiangyang","family":"Luo","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Zhu","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunfei","family":"Liu","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijian","family":"Lin","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Wan","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijian","family":"Cai","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shao-Lun","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVMP.2009.29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00112"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1399504.1360638"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref6","first-page":"1","article-title":"Real-time eye blink detection using facial landmarks","author":"Cech","year":"2016","journal-title":"Cent. Mach. Perception, Dep. Cybern. Fac. Electr. Eng. Czech Tech. Univ. Prague"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413630"},{"key":"ref8","article-title":"Hifivfs: High fidelity video face swapping","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00142"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00520"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547838"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00341"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref18","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6721"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_2"},{"key":"ref21","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111451"},{"key":"ref26","article-title":"Faceshifter: Towards high fidelity and occlusion aware face swapping","author":"Li","year":"2020","journal-title":"CVPR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681046"},{"key":"ref28","article-title":"Humanaesexpert: Advancing a multi-modality foundation model for human image aesthetic assessment","author":"Liao","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Teaser: Token enhanced spatial modeling for expressions reconstruction","author":"Liu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00829"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681120"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/AINA.2017.53"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275075"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3155571"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref40","article-title":"Vividface: A diffusion-based hybrid framework for high-fidelity video face swapping","author":"Shao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00702"},{"key":"ref42","article-title":"First order motion model for image animation","volume":"32","author":"Siarohin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","article-title":"Dynamicface: High-quality and consistent video face swapping using composable 3d facial priors","author":"Wang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32874"},{"key":"ref48","article-title":"Spf-portrait: Towards pure portrait customization with semantic pollution-free fine-tuning","author":"Xian","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00081"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00749"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_38"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3594034"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00829"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00828"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00480"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3369853"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445921.pdf?arnumber=11445921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:16Z","timestamp":1777613596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00938","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}