{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T15:14:53Z","timestamp":1769267693635,"version":"3.49.0"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"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":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tcsvt.2024.3349909","type":"journal-article","created":{"date-parts":[[2024,1,4]],"date-time":"2024-01-04T20:12:28Z","timestamp":1704399148000},"page":"5466-5479","source":"Crossref","is-referenced-by-count":5,"title":["Identity-Aware Variational Autoencoder for Face Swapping"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4181-310X","authenticated-orcid":false,"given":"Zonglin","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}]},{"given":"Zhaoxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Victoria Street, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3902-7510","authenticated-orcid":false,"given":"Quanling","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5200-3420","authenticated-orcid":false,"given":"Shengping","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3423-1539","authenticated-orcid":false,"given":"Bineng","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and the School of Software, Guangxi Normal University, Guilin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9163-2932","authenticated-orcid":false,"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Information, Xiamen University, Xiamen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVMP.2009.29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925871"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2004.00799.x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16811-1_11"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413630"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00505"},{"key":"ref8","article-title":"FaceShifter: Towards high fidelity and occlusion aware face swapping","author":"Li","year":"2019","journal-title":"arXiv:1912.13457"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16417"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.527"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322984"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00749"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00748"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01051"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_38"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref18","first-page":"1","article-title":"Image-to-image translation for cross-domain disentanglement","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Gonzalez-Garcia"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3109419"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1210384"},{"key":"ref21","first-page":"1","article-title":"Learning disentangled representations with semi-supervised deep generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Paige"},{"key":"ref22","article-title":"Disentangling factors of variation via generative entangling","author":"Desjardins","year":"2012","journal-title":"arXiv:1210.5474"},{"key":"ref23","first-page":"1","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Chen"},{"key":"ref24","first-page":"1","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Higgins"},{"key":"ref25","article-title":"Variational inference of disentangled latent concepts from unlabeled observations","author":"Kumar","year":"2017","journal-title":"arXiv:1711.00848"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20369"},{"key":"ref27","first-page":"1","article-title":"Isolating sources of disentanglement in variational autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chen"},{"key":"ref28","first-page":"1","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Hsu"},{"key":"ref29","first-page":"1","article-title":"Unsupervised learning of disentangled representations from video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Denton"},{"key":"ref30","article-title":"Decomposing motion and content for natural video sequence prediction","author":"Villegas","year":"2017","journal-title":"arXiv:1706.08033"},{"key":"ref31","first-page":"1","article-title":"Weakly-supervised disentangling with recurrent transformations for 3D view synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Yang"},{"key":"ref32","first-page":"1","article-title":"Deep convolutional inverse graphics network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Kulkarni"},{"key":"ref33","article-title":"3D morphable model based face replacement in video","volume-title":"ACM Special Interest Group on Computer Graphics","author":"Cheng","year":"2009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.305"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/157"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3130196"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3089724"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3106047"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00480"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00341"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_4"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00767"},{"key":"ref44","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref46","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref47","article-title":"Meta-GMVAE: Mixture of Gaussian VAEs for unsupervised meta-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref48","article-title":"Tutorial on variational autoencoders","author":"Doersch","year":"2016","journal-title":"arXiv:1606.05908"},{"key":"ref49","article-title":"WeLa-VAE: Learning alternative disentangled representations using weak labels","author":"Margonis","year":"2020","journal-title":"arXiv:2008.09879"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00016"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2021.104867"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1147\/rd.41.0066"},{"key":"ref53","first-page":"661","article-title":"Symmetric variational autoencoder and connections to adversarial learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Chen"},{"key":"ref54","first-page":"2552","article-title":"Density ratio estimation via infinitesimal classification","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Choi"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273507"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3176055"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.72"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref59","volume-title":"Deepfakes GitHub","year":"2021"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00829"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00091"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref66","volume-title":"FaceSwap GitHub","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref70","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"Karras","year":"2017","journal-title":"arXiv:1710.10196"},{"key":"ref71","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00664"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref75","volume-title":"Gaze Estimation GitHub","year":"2020"},{"key":"ref76","first-page":"1","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref77","article-title":"Learning disentangled representation for one-shot progressive face swapping","author":"Li","year":"2022","journal-title":"arXiv:2203.12985"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00828"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3074259"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3133859"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3209336"},{"key":"ref82","article-title":"Learning disentangled representations with reference-based variational autoencoders","author":"Ruiz","year":"2019","journal-title":"arXiv:1901.08534"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_49"},{"key":"ref84","first-page":"2649","article-title":"Disentangling by factorising","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093548"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00091"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10582818\/10380597.pdf?arnumber=10380597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:13:03Z","timestamp":1736453583000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10380597\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":86,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3349909","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7]]}}}