{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T13:30:47Z","timestamp":1777901447633,"version":"3.51.4"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T00:00:00Z","timestamp":1673481600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T00:00:00Z","timestamp":1673481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s11263-022-01742-1","type":"journal-article","created":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T08:03:43Z","timestamp":1673510623000},"page":"1122-1140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Expression-Preserving Face Frontalization Improves Visually Assisted Speech Processing"],"prefix":"10.1007","volume":"131","author":[{"given":"Zhiqi","family":"Kang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mostafa","family":"Sadeghi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5232-024X","authenticated-orcid":false,"given":"Radu","family":"Horaud","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,12]]},"reference":[{"key":"1742_CR1","doi-asserted-by":"crossref","unstructured":"Abdelaziz, A. H. (2017) NTCD-TIMIT: A new database and baseline for noise-robust audio-visual speech recognition. In: INTERSPEECH, pp 3752\u20133756.","DOI":"10.21437\/Interspeech.2017-860"},{"key":"1742_CR2","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1109\/TETCI.2019.2917039","volume":"5","author":"A Adeel","year":"2019","unstructured":"Adeel, A., Gogate, M., Hussain, A., & Whitmer, W. M. (2019). Lip-reading driven deep learning approach for speech enhancement. IEEE Transactions on Emerging Topics in Computational Intelligence, 5, 481.","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"issue":"3","key":"1742_CR3","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1109\/TETCI.2019.2917039","volume":"5","author":"A Adeel","year":"2021","unstructured":"Adeel, A., Gogate, M., Hussain, A., & Whitmer, W. M. (2021). Lip-reading driven deep learning approach for speech enhancement. IEEE Transactions on Emerging Topics in Computational Intelligence, 5(3), 481\u2013490.","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"1742_CR4","first-page":"1","volume":"1","author":"I Anina","year":"2015","unstructured":"Anina, I., Zhou, Z., Zhao, G., & Pietik\u00e4inen, M. (2015). OuluVS2: A multi-view audiovisual database for non-rigid mouth motion analysis. International Conference on Automatic Face and Gesture Recognition, 1, 1\u20135.","journal-title":"International Conference on Automatic Face and Gesture Recognition"},{"key":"1742_CR5","doi-asserted-by":"crossref","unstructured":"Banerjee, S., Brogan, J., Krizaj, J., Bharati, A., Webster, B. R., Struc, V., Flynn, P.J., & Scheirer, W.J. (2018). To frontalize or not to frontalize: Do we really need elaborate pre-processing to improve face recognition? In IEEE Winter conference on applications of computer vision, pp 20\u201329.","DOI":"10.1109\/WACV.2018.00009"},{"issue":"5","key":"1742_CR6","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/S0262-8856(97)00065-6","volume":"16","author":"A Baumberg","year":"1998","unstructured":"Baumberg, A. (1998). Hierarchical shape fitting using an iterated linear filter. Image and Vision Computing, 16(5), 329\u2013335.","journal-title":"Image and Vision Computing"},{"key":"1742_CR7","volume-title":"Pattern Recognition and Machine Learning","author":"C Bishop","year":"2006","unstructured":"Bishop, C. (2006). Pattern Recognition and Machine Learning. Springer."},{"key":"1742_CR8","first-page":"187","volume":"99","author":"V Blanz","year":"1999","unstructured":"Blanz, V., & Vetter, T. (1999). A morphable model for the synthesis of 3D faces. ACM SIGGRAPH, 99, 187\u2013194.","journal-title":"ACM SIGGRAPH"},{"key":"1742_CR9","doi-asserted-by":"crossref","unstructured":"Bulat, A., & Tzimiropoulos, G. (2016). Two-stage convolutional part heatmap regression for the 1st 3D face alignment in the wild (3DFAW) challenge. In European conference on computer vision workshops, Springer, pp 616\u2013624.","DOI":"10.1007\/978-3-319-48881-3_43"},{"issue":"3","key":"1742_CR10","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1109\/TVCG.2013.249","volume":"20","author":"C Cao","year":"2014","unstructured":"Cao, C., Weng, Y., Zhou, S., Tong, Y., & Zhou, K. (2014). Facewarehouse: A 3d facial expression database for visual computing. IEEE Transactions on Visualization and Computer Graphics, 20(3), 413\u2013425.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"1742_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, S., Ma, P., Tzimiropoulos, G., Petridis, S., Bulat, A., Shen, J., & Pantic, M. (2020). Towards pose-invariant lip-reading. In IEEE International conference on acoustics, speech and signal processing. pp 4357\u20134361.","DOI":"10.1109\/ICASSP40776.2020.9054384"},{"key":"1742_CR12","doi-asserted-by":"crossref","unstructured":"Chung, J. S., & Zisserman, A. (2016). Lip reading in the wild. In Asian Conference on computer vision, pp 87\u2013103.","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"1742_CR13","doi-asserted-by":"crossref","unstructured":"Deng, J., Zhou, Y., Cheng, S., & Zaferiou, S. (2018). Cascade multi-view hourglass model for robust 3d face alignment. In IEEE International conference on automatic face & gesture recognition, IEEE, pp 399\u2013403.","DOI":"10.1109\/FG.2018.00064"},{"key":"1742_CR14","doi-asserted-by":"crossref","unstructured":"Feng, Y., Wu, F., Shao, X., Wang, Y., & Zhou, X. (2018). Joint 3D face reconstruction and dense alignment with position map regression network. In European conference on computer vision, pp 534\u2013551.","DOI":"10.1007\/978-3-030-01264-9_33"},{"key":"1742_CR15","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.imavis.2018.07.002","volume":"78","author":"A Fernandez-Lopez","year":"2018","unstructured":"Fernandez-Lopez, A., & Sukno, F. M. (2018). Survey on automatic lip-reading in the era of deep learning. Image and Vision Computing, 78, 53\u201372.","journal-title":"Image and Vision Computing"},{"key":"1742_CR16","doi-asserted-by":"crossref","unstructured":"Ferrari, C., Lisanti, G., Berretti, S., & Del\u00a0Bimbo, A. (2016). Effective 3D based frontalization for unconstrained face recognition. In International conference on pattern recognition, IEEE, pp 1047\u20131052.","DOI":"10.1109\/ICPR.2016.7899774"},{"issue":"6","key":"1742_CR17","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1007\/s11222-013-9414-4","volume":"24","author":"F Forbes","year":"2014","unstructured":"Forbes, F., & Wraith, D. (2014). A new family of multivariate heavy-tailed distributions with variable marginal amounts of tailweight: Application to robust clustering. Statistics and Computing, 24(6), 971\u2013984.","journal-title":"Statistics and Computing"},{"issue":"1","key":"1742_CR18","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1109\/TSMCA.2007.909557","volume":"38","author":"W Gao","year":"2007","unstructured":"Gao, W., Cao, B., Shan, S., Chen, X., Zhou, D., Zhang, X., & Zhao, D. (2007). The CAS-PEAL large-scale Chinese face database and baseline evaluations. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, 38(1), 149\u2013161.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans"},{"issue":"5","key":"1742_CR19","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1016\/j.imavis.2009.08.002","volume":"28","author":"R Gross","year":"2010","unstructured":"Gross, R., Matthews, I., Cohn, J., Kanade, T., & Baker, S. (2010). Multi-PIE. Image and Vision Computing, 28(5), 807\u2013813.","journal-title":"Image and Vision Computing"},{"key":"1742_CR20","doi-asserted-by":"crossref","unstructured":"Hassner, T., Harel, S., Paz, E., & Enbar, R. (2015). Effective face frontalization in unconstrained images. In IEEE Conference on Computer Vision and Pattern Recognition, pp 4295\u20134304.","DOI":"10.1109\/CVPR.2015.7299058"},{"key":"1742_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"4","key":"1742_CR22","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1364\/JOSAA.4.000629","volume":"4","author":"BK Horn","year":"1987","unstructured":"Horn, B. K. (1987). Closed-form solution of absolute orientation using unit quaternions. Journal of the Optical Society of America A, 4(4), 629\u2013642.","journal-title":"Journal of the Optical Society of America A"},{"issue":"2","key":"1742_CR23","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TETCI.2017.2784878","volume":"2","author":"JC Hou","year":"2018","unstructured":"Hou, J. C., Wang, S. S., Lai, Y. H., Tsao, Y., Chang, H. W., & Wang, H. M. (2018). Audio-visual speech enhancement using multimodal deep convolutional neural networks. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(2), 117\u2013128.","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"1742_CR24","unstructured":"Huang, G. B., Mattar, M., Berg, T., & Learned-Miller, E. (2008). Labeled faces in the wild: A database for studying face recognition in unconstrained environments."},{"key":"1742_CR25","doi-asserted-by":"crossref","unstructured":"Huang, R., Zhang, S., Li, T., & He, R. (2017). Beyond face rotation: Global and local perception GAN for photorealistic and identity preserving frontal view synthesis. In IEEE International Conference on Computer Vision, pp 2439\u20132448.","DOI":"10.1109\/ICCV.2017.267"},{"key":"1742_CR26","doi-asserted-by":"crossref","unstructured":"Jiang, L., Wu, X. J., & Kittler, J. (2019). Dual attention mobdensenet (damdnet) for robust 3D face alignment. In Proceedings of the IEEE\/CVF international conference on computer vision workshops.","DOI":"10.1109\/ICCVW.2019.00063"},{"key":"1742_CR27","doi-asserted-by":"crossref","unstructured":"Kang, Z., Horaud, R., & Sadeghi, M. (2021). Robust face frontalization for visual speech recognition. In Proceedings of the IEEE\/CVF International conference on computer vision workshops, pp 2485\u20132495.","DOI":"10.1109\/ICCVW54120.2021.00281"},{"issue":"2","key":"1742_CR28","first-page":"87","volume":"4","author":"DG Kendall","year":"1989","unstructured":"Kendall, D. G. (1989). A survey of the statistical theory of shape. Statistical Science, 4(2), 87\u201399.","journal-title":"Statistical Science"},{"key":"1742_CR29","unstructured":"Kingma, D. P., & Welling, M. (2014). Auto-encoding variational bayes. In ICLR."},{"key":"1742_CR30","unstructured":"Kraft, D. (1988). A software package for sequential quadratic programming. Tech. Rep. DFVLR-FB 88-28, DLR German Aerospace Center\u2014Institute for Flight Mechanics, Koln, Germany."},{"key":"1742_CR31","doi-asserted-by":"crossref","unstructured":"Le\u00a0Roux, J., Wisdom, S., Erdogan, H., & Hershey, J. R. (2019). SDR\u2013half-baked or well done? In ICASSP.","DOI":"10.1109\/ICASSP.2019.8683855"},{"issue":"1","key":"1742_CR32","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1049\/iet-cvi:20045243","volume":"1","author":"S Lee","year":"2007","unstructured":"Lee, S., Kang, J., Shin, J., & Paik, J. (2007). Hierarchical active shape model with motion prediction for real-time tracking of non-rigid objects. IET Computer Vision, 1(1), 17\u201324.","journal-title":"IET Computer Vision"},{"key":"1742_CR33","doi-asserted-by":"crossref","unstructured":"Leglaive, S., Girin, L., & Horaud, R. (2018) A variance modeling framework based on variational autoencoders for speech enhancement. In MLSP.","DOI":"10.1109\/MLSP.2018.8516711"},{"key":"1742_CR34","doi-asserted-by":"crossref","unstructured":"Ma, P., Martinez, B., Petridis, S., & Pantic, M. (2021a). Towards practical lipreading with distilled and efficient models. IEEE International conference on acoustics (pp. 7608\u20137612). IEEE: Speech and Signal Processing.","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"1742_CR35","doi-asserted-by":"crossref","unstructured":"Ma, P., Martinez, B., Petridis, S., & Pantic, M. (2021b). Lip-reading with densely connected temporal convolutional networks. In IEEE Winter conference on applications of computer vision.","DOI":"10.1109\/WACV48630.2021.00290"},{"key":"1742_CR36","doi-asserted-by":"crossref","unstructured":"Martinez, B., Ma, P., Petridis, S., & Pantic, M. (2020). Lipreading using temporal convolutional networks. In IEEE International conference on acoustics, speech and signal processing, pp 6319\u20136323.","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"issue":"7","key":"1742_CR37","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1016\/S0378-2166(99)00079-X","volume":"32","author":"EZ McClave","year":"2000","unstructured":"McClave, E. Z. (2000). Linguistic functions of head movements in the context of speech. Journal of Pragmatics, 32(7), 855\u2013878.","journal-title":"Journal of Pragmatics"},{"key":"1742_CR38","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","volume":"24","author":"M McCloskey","year":"1989","unstructured":"McCloskey, M., & Cohen, N. J. (1989). Catastrophic interference in connectionist networks: The sequential learning problem. Psychology of Learning and Motivation, 24, 109\u2013165.","journal-title":"Psychology of Learning and Motivation"},{"key":"1742_CR39","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1109\/TASLP.2021.3066303","volume":"29","author":"D Michelsanti","year":"2021","unstructured":"Michelsanti, D., Tan, Z. H., Zhang, S. X., Xu, Y., Yu, M., Yu, D., & Jensen, J. (2021). An overview of deep-learning-based audio-visual speech enhancement and separation. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 29, 1368\u20131396.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"1742_CR40","doi-asserted-by":"publisher","first-page":"1944","DOI":"10.1109\/LSP.2020.3032277","volume":"27","author":"X Ning","year":"2020","unstructured":"Ning, X., Duan, P., Li, W., & Zhang, S. (2020). Real-time 3d face alignment using an encoder-decoder network with an efficient deconvolution layer. IEEE Signal Processing Letters, 27, 1944\u20131948.","journal-title":"IEEE Signal Processing Letters"},{"key":"1742_CR41","doi-asserted-by":"crossref","unstructured":"Paysan P, Knothe R, Amberg B, Romdhani S, & Vetter T (2009) A 3D face model for pose and illumination invariant face recognition. In: IEEE International Conference on Advanced Video and Signal Based Surveillance, pp 296\u2013301","DOI":"10.1109\/AVSS.2009.58"},{"issue":"4","key":"1742_CR42","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1023\/A:1008981510081","volume":"10","author":"D Peel","year":"2000","unstructured":"Peel, D., & McLachlan, G. J. (2000). Robust mixture modelling using the t distribution. Statistics and Computing, 10(4), 339\u2013348.","journal-title":"Statistics and Computing"},{"key":"1742_CR43","doi-asserted-by":"crossref","unstructured":"Pei, E., Oveneke, M.C., Zhao, Y., Jiang, D., & Sahli, H. (2020). Monocular 3d facial expression features for continuous affect recognition. IEEE Transactions on Multimedia.","DOI":"10.1109\/TMM.2020.3026894"},{"key":"1742_CR44","doi-asserted-by":"crossref","unstructured":"Prabhu, U., Seshadri, K., Savvides, M. (2010). Automatic facial landmark tracking in video sequences using Kalman filter assisted active shape models. In European conference on computer vision, Springer, pp 86\u201399.","DOI":"10.1007\/978-3-642-35749-7_7"},{"key":"1742_CR45","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.media.2017.11.012","volume":"44","author":"N Ravikumar","year":"2018","unstructured":"Ravikumar, N., Gooya, A., \u00c7imen, S., Frangi, A. F., & Taylor, Z. A. (2018). Group-wise similarity registration of point sets using Student\u2019s t-mixture model for statistical shape models. Medical Image Analysis, 44, 156\u2013176.","journal-title":"Medical Image Analysis"},{"key":"1742_CR46","unstructured":"Rix, A. W., Beerends, J. G., Hollier, M. P., & Hekstra, A. P. (2001) Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In ICASSP."},{"key":"1742_CR47","doi-asserted-by":"publisher","first-page":"68842","DOI":"10.1109\/ACCESS.2020.2986079","volume":"8","author":"C Rong","year":"2020","unstructured":"Rong, C., Zhang, X., & Lin, Y. (2020). Feature-improving generative adversarial network for face frontalization. IEEE Access, 8, 68842\u201368851.","journal-title":"IEEE Access"},{"key":"1742_CR48","doi-asserted-by":"publisher","first-page":"1899","DOI":"10.1109\/TSP.2021.3066038","volume":"69","author":"M Sadeghi","year":"2021","unstructured":"Sadeghi, M., & Alameda-Pineda, X. (2021). Mixture of inference networks for VAE-based audio-visual speech enhancement. IEEE Transactions on Signal Processing, 69, 1899\u20131909.","journal-title":"IEEE Transactions on Signal Processing"},{"key":"1742_CR49","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1109\/TASLP.2020.3000593","volume":"28","author":"M Sadeghi","year":"2020","unstructured":"Sadeghi, M., Leglaive, S., Alameda-Pineda, X., Girin, L., & Horaud, R. (2020). Audio-visual speech enhancement using conditional variational auto-encoders. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 28, 1788\u20131800.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"1742_CR50","doi-asserted-by":"crossref","unstructured":"Sariyanidi, E., Zampella, C. J., Schultz, R. T., & Tunc, B. (2020). Can facial pose and expression be separated with weak perspective camera? In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7173\u20137182.","DOI":"10.1109\/CVPR42600.2020.00720"},{"issue":"12","key":"1742_CR51","doi-asserted-by":"publisher","first-page":"2257","DOI":"10.1109\/TASLP.2017.2752365","volume":"25","author":"T Schultz","year":"2017","unstructured":"Schultz, T., Wand, M., Hueber, T., Krusienski, D. J., Herff, C., & Brumberg, J. S. (2017). Biosignal-based spoken communication: A survey. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 25(12), 2257\u20132271.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"issue":"1\u20133","key":"1742_CR52","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1023\/A:1014585622703","volume":"47","author":"C Sun","year":"2002","unstructured":"Sun, C. (2002). Fast stereo matching using rectangular subregioning and 3D maximum-surface techniques. International Journal of Computer Vision, 47(1\u20133), 99\u2013117.","journal-title":"International Journal of Computer Vision"},{"issue":"7","key":"1742_CR53","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1109\/TASL.2011.2114881","volume":"19","author":"CH Taal","year":"2011","unstructured":"Taal, C. H., Hendriks, R. C., Heusdens, R., & Jensen, J. (2011). An algorithm for intelligibility prediction of time-frequency weighted noisy speech. IEEE Trans Audio, Speech, Language Process, 19(7), 2125\u20132136.","journal-title":"IEEE Trans Audio, Speech, Language Process"},{"key":"1742_CR54","unstructured":"Thiemann, J., Ito, N., & Vincent, E. (2013). Demand: A collection of multi-channel recordings of acoustic noise in diverse environments. In Proceedings of Meetings on Acoustics, pp 1\u20136."},{"key":"1742_CR55","doi-asserted-by":"crossref","unstructured":"Tran, L., Yin, X., & Liu, X. (2017) Disentangled representation learning GAN for pose-invariant face recognition. In IEEE Conference on Computer Vision and Pattern Recognition, pp 1415\u20131424.","DOI":"10.1109\/CVPR.2017.141"},{"key":"1742_CR56","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/TMM.2020.2993962","volume":"23","author":"X Tu","year":"2020","unstructured":"Tu, X., Zhao, J., Jiang, Z., Luo, Y., Xie, M., Zhao, Y., He, L., Ma, Z., & Feng, J. (2020). 3d face reconstruction from a single image assisted by 2d face images in the wild. IEEE Transactions on Multimedia, 23, 1160\u20131172.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1742_CR57","doi-asserted-by":"crossref","unstructured":"Wang, K., Wu, Q., Song, L., Yang, Z., Wu, W., Qian, C., He, R., Qiao, Y., & Loy, C. C. (2020). MEAD: A large-scale audio-visual dataset for emotional talking-face generation. In ECCV, Springer.","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"1742_CR58","unstructured":"Yim, J., Jung, H., Yoo, B., Choi, C., Park, D., & Kim, J. (2015). Rotating your face using multi-task deep neural network. In IEEE Conference on computer vision and pattern recognition, pp 676\u2013684."},{"key":"1742_CR59","doi-asserted-by":"crossref","unstructured":"Yin, X., Yu, X., Sohn, K., Liu, X., & Chandraker, M. (2017). Towards large-pose face frontalization in the wild. In IEEE International Conference on Computer Vision, pp 3990\u20133999.","DOI":"10.1109\/ICCV.2017.430"},{"key":"1742_CR60","doi-asserted-by":"crossref","unstructured":"Yin, Y., Jiang, S., Robinson, J. P., Fu, Y. (2020). Dual-attention GAN for large-pose face frontalization. In IEEE International Conference on Automatic Face and Gesture Recognition, pp 24\u201331.","DOI":"10.1109\/FG47880.2020.00004"},{"issue":"5","key":"1742_CR61","doi-asserted-by":"publisher","first-page":"2187","DOI":"10.1109\/TIP.2018.2883554","volume":"28","author":"Z Zhang","year":"2019","unstructured":"Zhang, Z., Chen, X., Wang, B., Hu, G., Zuo, W., & Hancock, E. R. (2019). Face frontalization using an appearance-flow-based convolutional neural network. IEEE Transactions on Image Processing, 28(5), 2187\u20132199.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1742_CR62","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1109\/TIFS.2020.3025412","volume":"16","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., Liang, R., Chen, X., Xu, X., Hu, G., Zuo, W., & Hancock, E. R. (2021). Semi-supervised face frontalization in the wild. IEEE Transactions on Information Forensics and Security, 16, 909\u2013922.","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"1742_CR63","doi-asserted-by":"crossref","unstructured":"Zhao, J., Cheng, Y., Xu, Y., Xiong, L., Li, J., Zhao, F., Jayashree, K., Pranata, S., Shen, S., Xing, J., & Yan, S. (2018). Towards pose invariant face recognition in the wild. In IEEE conference on computer vision and pattern recognition, pp 2207\u20132216.","DOI":"10.1109\/CVPR.2018.00235"},{"key":"1742_CR64","doi-asserted-by":"crossref","unstructured":"Zhou, E., Cao, Z., & Sun, J. (2018) Gridface: Face rectification via learning local homography transformations. In Proceedings of the European Conference on Computer Vision.","DOI":"10.1007\/978-3-030-01270-0_1"},{"key":"1742_CR65","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, J., Liu, Z., Liu, Y., Wang, X. (2020). Rotate-and-render: Unsupervised photorealistic face rotation from single-view images. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00595"},{"issue":"3","key":"1742_CR66","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0091381","volume":"9","author":"Z Zhou","year":"2014","unstructured":"Zhou, Z., Zheng, J., Dai, Y., Zhou, Z., & Chen, S. (2014). Robust non-rigid point set registration using student\u2019s-t mixture model. PloS One, 9(3), e91381.","journal-title":"PloS One"},{"key":"1742_CR67","doi-asserted-by":"crossref","unstructured":"Zhu, J. Y., Park, T., Isola, P., Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pp 2223\u20132232.","DOI":"10.1109\/ICCV.2017.244"},{"key":"1742_CR68","unstructured":"Zhu, X., Lei, Z., Yan, J., Yi, D., Li, & S. Z. (2015). High-fidelity pose and expression normalization for face recognition in the wild. In IEEE conference on computer vision and pattern recognition, pp 787\u2013796."},{"key":"1742_CR69","doi-asserted-by":"crossref","unstructured":"Zhu, X., Lei, Z., Liu, X., Shi, H., & Li, S. Z. (2016). Face alignment across large poses: A 3D solution. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 146\u2013155.","DOI":"10.1109\/CVPR.2016.23"},{"issue":"1","key":"1742_CR70","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1109\/TPAMI.2017.2778152","volume":"41","author":"X Zhu","year":"2019","unstructured":"Zhu, X., Liu, X., Lei, Z., & Li, S. Z. (2019). Face alignment in full pose range: A 3d total solution. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(1), 78\u201392.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01742-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01742-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01742-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T09:17:44Z","timestamp":1681377464000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01742-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,12]]},"references-count":70,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["1742"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01742-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,12]]},"assertion":[{"value":"15 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 December 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}