{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T10:49:56Z","timestamp":1761648596623,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2018,12,15]],"date-time":"2018-12-15T00:00:00Z","timestamp":1544832000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004543","name":"Chinese Scholarship Council","doi-asserted-by":"crossref","award":["201506290085"],"award-info":[{"award-number":["201506290085"]}],"id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shaanxi Provincial International Science and Technology Collaboration Project","award":["2017KW-ZD-14"],"award-info":[{"award-number":["2017KW-ZD-14"]}]},{"name":"VUB Interdisciplinary Research Program through the EMO-App project, and the Agency for Innovation by Science and Technology in Flanders","award":["131814"],"award-info":[{"award-number":["131814"]}]},{"DOI":"10.13039\/501100001809","name":"the Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61273265"],"award-info":[{"award-number":["61273265"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s11042-018-6952-y","type":"journal-article","created":{"date-parts":[[2018,12,15]],"date-time":"2018-12-15T06:20:14Z","timestamp":1544854814000},"page":"16389-16410","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A video prediction approach for animating single face image"],"prefix":"10.1007","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2644-952X","authenticated-orcid":false,"given":"Yong","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meshia C\u00e9dric","family":"Oveneke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hichem","family":"Sahli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,15]]},"reference":[{"issue":"1","key":"6952_CR1","first-page":"3563","volume":"15","author":"G Alain","year":"2014","unstructured":"Alain G, Bengio Y (2014) What regularized auto-encoders learn from the data-generating distribution. J Mach Learn Res 15(1):3563\u20133593","journal-title":"J Mach Learn Res"},{"key":"6952_CR2","doi-asserted-by":"crossref","unstructured":"Anderson R, Stenger B, Wan V, Cipolla R (2013) Expressive visual text-to-speech using active appearance models. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3382\u20133389","DOI":"10.1109\/CVPR.2013.434"},{"issue":"6","key":"6952_CR3","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1145\/3130800.3130818","volume":"36","author":"H Averbuch-Elor","year":"2017","unstructured":"Averbuch-Elor H, Cohen-Or D, Kopf J, Cohen MF (2017) Bringing portraits to life. ACM Trans Graph (TOG) 36(6):196","journal-title":"ACM Trans Graph (TOG)"},{"issue":"8","key":"6952_CR4","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 35(8):1798\u20131828","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6952_CR5","doi-asserted-by":"crossref","unstructured":"Blanz V, Vetter T (1999) A morphable model for the synthesis of 3d faces. In: Proceedings of the 26th annual conference on computer graphics and interactive techniques. ACM Press\/Addison-Wesley Publishing Co., pp 187\u2013194","DOI":"10.1145\/311535.311556"},{"key":"6952_CR6","doi-asserted-by":"crossref","unstructured":"Blanz V, Basso C, Poggio T, Vetter T (2003) Reanimating faces in images and video. In: Computer graphics forum vol 22. Wiley Online Library, pp 641\u2013650","DOI":"10.1111\/1467-8659.t01-1-00712"},{"issue":"4","key":"6952_CR7","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1145\/1095878.1095881","volume":"24","author":"Y Cao","year":"2005","unstructured":"Cao Y, Tien WC, Faloutsos P, Pighin F (2005) Expressive speech-driven facial animation. ACM Trans Graph (TOG) 24(4):1283\u20131302","journal-title":"ACM Trans Graph (TOG)"},{"issue":"4","key":"6952_CR8","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1145\/2897824.2925873","volume":"35","author":"C Cao","year":"2016","unstructured":"Cao C, Wu H, Weng Y, Shao T, Zhou K (2016) Real-time facial animation with image-based dynamic avatars. ACM Trans Graph (TOG) 35(4):126","journal-title":"ACM Trans Graph (TOG)"},{"issue":"6","key":"6952_CR9","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1109\/34.927467","volume":"23","author":"TF Cootes","year":"2001","unstructured":"Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Pattern Anal Mach Intell 23(6):681\u2013685","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6952_CR10","unstructured":"Deng Z, Noh J (2008) Computer facial animation: a survey. In: Data-driven 3D facial animation. Springer, pp 1\u201328"},{"key":"6952_CR11","doi-asserted-by":"crossref","unstructured":"Ding H, Zhou SK, Chellappa R (2017) Facenet2expnet: regularizing a deep face recognition net for expression recognition. In: 2017 12th IEEE International conference on automatic face & gesture recognition (FG 2017). IEEE, pp 118\u2013126","DOI":"10.1109\/FG.2017.23"},{"issue":"1","key":"6952_CR12","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s00371-007-0175-y","volume":"24","author":"N Ersotelos","year":"2008","unstructured":"Ersotelos N, Dong F (2008) Building highly realistic facial modeling and animation: a survey. Vis Comput 24(1):13\u201330","journal-title":"Vis Comput"},{"key":"6952_CR13","doi-asserted-by":"crossref","unstructured":"Fan B, Wang L, Soong FK, Xie L (2015) Photo-real talking head with deep bidirectional lstm. In: 2015 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 4884\u20134888","DOI":"10.1109\/ICASSP.2015.7178899"},{"issue":"3","key":"6952_CR14","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1145\/2890493","volume":"35","author":"P Garrido","year":"2016","unstructured":"Garrido P, Zollh\u00f6fer M, Casas D, Valgaerts L, Varanasi K, P\u00e9rez P, Theobalt C (2016) Reconstruction of personalized 3d face rigs from monocular video. ACM Trans Graph (TOG) 35(3):28","journal-title":"ACM Trans Graph (TOG)"},{"key":"6952_CR15","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672\u2013 2680"},{"issue":"4","key":"6952_CR16","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1145\/2766974","volume":"34","author":"AE Ichim","year":"2015","unstructured":"Ichim AE, Bouaziz S, Pauly M (2015) Dynamic 3d avatar creation from hand-held video input. ACM Trans Graph (TOG) 34(4):45","journal-title":"ACM Trans Graph (TOG)"},{"issue":"1","key":"6952_CR17","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/s11042-013-1610-x","volume":"73","author":"D Jiang","year":"2014","unstructured":"Jiang D, Zhao Y, Sahli H, Zhang Y (2014) Speech driven photo realistic facial animation based on an articulatory dbn model and aam features. Multimed Tools Appl 73(1):397\u2013415","journal-title":"Multimed Tools Appl"},{"key":"6952_CR18","unstructured":"Kingma DP, Welling M (2013) Auto-encoding variational bayes. arXiv: 13126114"},{"key":"6952_CR19","doi-asserted-by":"crossref","unstructured":"Liu Z, Shan Y, Zhang Z (2001) Expressive expression mapping with ratio images. In: Proceedings of the 28th annual conference on computer graphics and interactive techniques. ACM, pp 271\u2013276","DOI":"10.1145\/383259.383289"},{"key":"6952_CR20","doi-asserted-by":"crossref","unstructured":"Lucey P, Cohn JF, Kanade T, Saragih J, Ambadar Z, Matthews I (2010) The extended cohn-kanade dataset (ck+): a complete dataset for action unit and emotion-specified expression. In: 2010 IEEE Computer society conference on computer vision and pattern recognition workshops (CVPRW). IEEE, pp 94\u2013101","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"6952_CR21","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv: 14111784"},{"key":"6952_CR22","doi-asserted-by":"crossref","unstructured":"Olszewski K, Li Z, Yang C, Zhou Y, Yu R, Huang Z, Xiang S, Saito S, Kohli P, Li H (2017) Realistic dynamic facial textures from a single image using gans. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5429\u20135438","DOI":"10.1109\/ICCV.2017.580"},{"key":"6952_CR23","unstructured":"Oveneke MC, Aliosha-Perez M, Zhao Y, Jiang D, Sahli H (2016) Efficient convolutional auto-encoding via random convexification and frequency-domain minimization. arXiv: 161109232"},{"key":"6952_CR24","unstructured":"Oveneke MC, Zhao Y, Jiang D, Sahli H (2017) Expressive face frontalization and its application to facial expression analysis. Tech. rep., Vrije Universiteit Brussel"},{"key":"6952_CR25","unstructured":"Rifai S, Vincent P, Muller X, Glorot X, Bengio Y (2011) Contractive auto-encoders: explicit invariance during feature extraction. In: Proceedings of the 28th international conference on machine learning (ICML-11), pp 833\u2013840"},{"key":"6952_CR26","doi-asserted-by":"crossref","unstructured":"Shu Z, Yumer E, Hadap S, Sunkavalli K, Shechtman E, Samaras D (2017) Neural face editing with intrinsic image disentangling. arXiv: 170404131","DOI":"10.1109\/CVPR.2017.578"},{"key":"6952_CR27","doi-asserted-by":"crossref","unstructured":"Stoiber N, Seguier R, Breton G (2009) Automatic design of a control interface for a synthetic face. In: Proceedings of the 14th international conference on intelligent user interfaces. ACM, pp 207\u2013216","DOI":"10.1145\/1502650.1502681"},{"key":"6952_CR28","unstructured":"Susskind JM, Anderson AK, Hinton GE, Movellan JR (2008) Generating facial expressions with deep belief nets. INTECH Open Access Publisher"},{"key":"6952_CR29","unstructured":"Sutskever I, Hinton GE, Taylor GW (2009) The recurrent temporal restricted boltzmann machine. In: Advances in neural information processing systems, pp 1601\u20131608"},{"key":"6952_CR30","unstructured":"Taylor GW, Hinton GE (2009) Factored conditional restricted Boltzmann machines for modeling motion style. In: Proceedings of the 26th annual international conference on machine learning. ACM, pp 1025\u20131032"},{"key":"6952_CR31","first-page":"1345","volume":"19","author":"GW Taylor","year":"2007","unstructured":"Taylor GW, Hinton GE, Roweis ST (2007) Modeling human motion using binary latent variables. Adv Neural Inf Process Syst 19:1345","journal-title":"Adv Neural Inf Process Syst"},{"key":"6952_CR32","doi-asserted-by":"crossref","unstructured":"Thies J, Zollhofer M, Stamminger M, Theobalt C, Nie\u00dfner M (2016) Face2face: real-time face capture and reenactment of rgb videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2387\u20132395","DOI":"10.1145\/2929464.2929475"},{"key":"6952_CR33","doi-asserted-by":"crossref","unstructured":"Tulyakov S, Liu MY, Yang X, Kautz J (2018) Mocogan: decomposing motion and content for video generation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1526\u20131535","DOI":"10.1109\/CVPR.2018.00165"},{"key":"6952_CR34","unstructured":"Villegas R, Yang J, Zou Y, Sohn S, Lin X, Lee H (2017) Learning to generate long-term future via hierarchical prediction. arXiv: 170405831"},{"issue":"1","key":"6952_CR35","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/MSP.2008.930649","volume":"26","author":"Z Wang","year":"2009","unstructured":"Wang Z, Bovik AC (2009) Mean squared error: love it or leave it? A new look at signal fidelity measures. IEEE Signal Process Mag 26(1):98\u2013117","journal-title":"IEEE Signal Process Mag"},{"issue":"22","key":"6952_CR36","doi-asserted-by":"publisher","first-page":"9849","DOI":"10.1007\/s11042-014-2118-8","volume":"74","author":"L Wang","year":"2015","unstructured":"Wang L, Soong FK (2015) Hmm trajectory-guided sample selection for photo-realistic talking head. Multimed Tools Appl 74(22):9849\u20139869","journal-title":"Multimed Tools Appl"},{"issue":"4","key":"6952_CR37","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13 (4):600\u2013612","journal-title":"IEEE Trans Image Process"},{"key":"6952_CR38","doi-asserted-by":"crossref","unstructured":"Yan X, Yang J, Sohn K, Lee H (2016) Attribute2image: conditional image generation from visual attributes. In: European conference on computer vision. Springer, pp 776\u2013791","DOI":"10.1007\/978-3-319-46493-0_47"},{"issue":"9","key":"6952_CR39","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1016\/j.imavis.2011.07.002","volume":"29","author":"G Zhao","year":"2011","unstructured":"Zhao G, Huang X, Taini M, Li SZ, Pietik\u00e4Inen M (2011) Facial expression recognition from near-infrared videos. Image Vis Comput 29(9):607\u2013619","journal-title":"Image Vis Comput"},{"key":"6952_CR40","doi-asserted-by":"crossref","unstructured":"Zhao Y, Jiang D, Sahli H (2015) 3d emotional facial animation synthesis with factored conditional restricted Boltzmann machines. In: 2015 International conference on affective computing and intelligent interaction (ACII). IEEE, pp 797\u2013803","DOI":"10.1109\/ACII.2015.7344664"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6952-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6952-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6952-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T11:57:27Z","timestamp":1662638247000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6952-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,15]]},"references-count":40,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["6952"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6952-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2018,12,15]]},"assertion":[{"value":"30 December 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 November 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 December 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}