{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T11:19:13Z","timestamp":1790767153118,"version":"4.1.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2018,5,23]],"date-time":"2018-05-23T00:00:00Z","timestamp":1527033600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1007\/s11263-018-1095-1","type":"journal-article","created":{"date-parts":[[2018,5,23]],"date-time":"2018-05-23T15:01:17Z","timestamp":1527087677000},"page":"1103-1119","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["RED-Net: A Recurrent Encoder\u2013Decoder Network for Video-Based Face Alignment"],"prefix":"10.1007","volume":"126","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7772-001X","authenticated-orcid":false,"given":"Xi","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rogerio S.","family":"Feris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitris N.","family":"Metaxas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,5,23]]},"reference":[{"key":"1095_CR1","unstructured":"Asthana, A., Zafeiriou, S., Cheng, S., & Pantic, M. (2003). Robust discriminative response map fitting with constrained local models. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3444\u20133451)."},{"key":"1095_CR2","doi-asserted-by":"crossref","unstructured":"Asthana, A., Zafeiriou, S., Cheng, S., & Pantic, M. (2014). Incremental face alignment in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2014.240"},{"key":"1095_CR3","unstructured":"Badrinarayanan, V., Kendall, A., & Cipolla, R. (2015). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. CoRR."},{"key":"1095_CR4","doi-asserted-by":"crossref","unstructured":"Belhumeur, P. N., Jacobs, D. W., Kriegman, D. J., & Kumar, N. (2011). Localizing parts of faces using a consensus of exemplars. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2011.5995602"},{"key":"1095_CR5","doi-asserted-by":"crossref","unstructured":"Black, M., & Yacoob, Y. (1995). Tracking and recognizing rigid and non-rigid facial motions using local parametric models of image motion. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/ICCV.1995.466915"},{"key":"1095_CR6","first-page":"717","volume-title":"Human pose estimation via convolutional part heatmap regression","author":"A Bulat","year":"2016","unstructured":"Bulat, A., & Tzimiropoulos, G. (2016). Human pose estimation via convolutional part heatmap regression (pp. 717\u2013732). Cham: Springer."},{"issue":"2","key":"1095_CR7","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s11263-013-0667-3","volume":"107","author":"X Cao","year":"2014","unstructured":"Cao, X., Wei, Y., Wen, F., & Sun, J. (2014). Face alignment by explicit shape regression. International Journal of Computer Vision, 107(2), 177\u2013190.","journal-title":"International Journal of Computer Vision"},{"key":"1095_CR8","unstructured":"Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. CoRR arXiv:1409.1259 ."},{"key":"1095_CR9","unstructured":"Chrysos, G. G., Antonakos, E., Zafeiriou, S., & Snape, P. (2015). Offline deformable face tracking in arbitrary videos. In: Proceedings of the IEEE international conference on computer vision workshop (pp. 954\u2013962)."},{"key":"1095_CR10","doi-asserted-by":"crossref","unstructured":"Cootes, T. F., & Taylor, C. J. (1992). Active shape models-smart snakes. In BMVC.","DOI":"10.1007\/978-1-4471-3201-1_28"},{"issue":"2","key":"1095_CR11","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1023\/A:1008122917811","volume":"38","author":"D Decarlo","year":"2000","unstructured":"Decarlo, D., & Metaxas, D. (2000). Optical flow constraints on deformable models with applications to face tracking. International Journal of Computer Vision, 38(2), 99\u2013127.","journal-title":"International Journal of Computer Vision"},{"key":"1095_CR12","unstructured":"FGNet: Talking face video. Technical report, Online (2004)"},{"issue":"2","key":"1095_CR13","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/TSMCC.2009.2035631","volume":"40","author":"X Gao","year":"2010","unstructured":"Gao, X., Su, Y., Li, X., & Tao, D. (2010). A review of active appearance models. IEEE Transactions on Systems, Man, and Cybernetics, 40(2), 145\u2013158.","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"1095_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"1095_CR15","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computing, 9(8), 1735\u20131780.","journal-title":"Neural Computing"},{"key":"1095_CR16","unstructured":"Hong, S., Noh, H., & Han, B. (2015). Decoupled deep neural network for semi-supervised semantic segmentation. CoRR arXiv:1506.04924 ."},{"key":"1095_CR17","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. CoRR arXiv:1502.03167 ."},{"key":"1095_CR18","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., et al. (2014). Caffe: Convolutional architecture for fast feature embedding. In ACM multimedia conference (pp. 675\u2013678).","DOI":"10.1145\/2647868.2654889"},{"key":"1095_CR19","doi-asserted-by":"crossref","unstructured":"Jourabloo, A., & Liu, X. (2016). Large-pose face alignment via CNN-based dense 3D model fitting. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.454"},{"key":"1095_CR20","doi-asserted-by":"crossref","unstructured":"Karpathy, A., & Fei-Fei, L. (2015). Deep visual-semantic alignments for generating image descriptions. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"1095_CR21","unstructured":"Kendall, A., Badrinarayanan, V., & Cipolla, R. (2015). Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. CoRR arXiv:1511.02680 ."},{"key":"1095_CR22","doi-asserted-by":"crossref","unstructured":"Koestinger, M., Wohlhart, P., Roth, P. M., & Bischof, H. (2011) Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization. In Workshop on benchmarking facial image analysis technologies.","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"1095_CR23","unstructured":"Lai, H., Xiao, S., Cui, Z., Pan, Y., Xu, C., & Yan, S. (2015). Deep cascaded regression for face alignment. arXiv:1510.09083v2 ."},{"key":"1095_CR24","doi-asserted-by":"crossref","unstructured":"Le, V., Brandt, J., Lin, Z., Bourdev, L., & Huang, T. S. (2012). Interactive facial feature localization. In European conference on computer vision (pp. 679\u2013692).","DOI":"10.1007\/978-3-642-33712-3_49"},{"key":"1095_CR25","unstructured":"Learned-Miller, G. B. H. E. (2014). Labeled faces in the wild: Updates and new reporting procedures. Technical Report UM-CS-2014-003, University of Massachusetts, Amherst."},{"key":"1095_CR26","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2014a). Fully convolutional networks for semantic segmentation. CoRR arXiv:1411.4038 .","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1095_CR27","unstructured":"Long, J. L., Zhang, N., & Darrell, T. (2014b). Do convnets learn correspondence? In Advances in neural information processing systems (pp. 1601\u20131609)."},{"key":"1095_CR28","doi-asserted-by":"crossref","unstructured":"Lu, L., Zhang, X., Cho, K., & Renals, S. (2015). A study of the recurrent neural network encoder-decoder for large vocabulary speech recognition. In INTERSPEECH.","DOI":"10.21437\/Interspeech.2015-654"},{"key":"1095_CR29","unstructured":"Mikolov, T., Joulin, A., Chopra, S., Mathieu, M., & Ranzato, M. (2014). Learning longer memory in recurrent neural networks. CoRR arXiv:1412.7753 ."},{"key":"1095_CR30","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., \u010cernock\u00fd, J., & Khudanpur, S. (2010). Recurrent neural network based language model. In INTERSPEECH.","DOI":"10.21437\/Interspeech.2010-343"},{"key":"1095_CR31","doi-asserted-by":"crossref","unstructured":"Milborrow, S., & Nicolls, F. (2008). Locating facial features with an extended active shape model. In European conference on computer vision (pp. 504\u2013513).","DOI":"10.1007\/978-3-540-88693-8_37"},{"key":"1095_CR32","unstructured":"Nair, V., & Hinton, G. E. (2010). Rectified linear units improve restricted Boltzmann machines. In The international conference on machine learning (pp. 807\u2013814)."},{"key":"1095_CR33","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R. L., & Singh, S. (2015). Action-conditional video prediction using deep networks in atari games. In Advances in neural information processing systems (pp. 2845\u20132853)."},{"key":"1095_CR34","doi-asserted-by":"crossref","unstructured":"Oliver, N., Pentland, A., & Berard, F. (1997). Lafter: Lips and face real time tracker. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 123\u2013129).","DOI":"10.1109\/CVPR.1997.609309"},{"key":"1095_CR35","unstructured":"Patras, I., & Pantic, M. (2004). Particle filtering with factorized likelihoodsfor tracking facial features. In Automatic face and gesture recognition (pp. 97\u2013102)."},{"key":"1095_CR36","doi-asserted-by":"crossref","unstructured":"Peng, X., Feris, R. S., Wang, X., & Metaxas, D. N. (2016a). A recurrent encoder-decoder network for sequential face alignment. In European conference on computer vision (pp. 38\u201356). Springer.","DOI":"10.1007\/978-3-319-46448-0_3"},{"key":"1095_CR37","doi-asserted-by":"crossref","unstructured":"Peng, X., Hu, Q., Huang, J., & Metaxas, D. N. (2016b). Track facial points in unconstrained videos. In Proceedings of the British machine vision conference (pp. 129.1\u2013129.13).","DOI":"10.5244\/C.30.129"},{"key":"1095_CR38","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.cviu.2015.03.008","volume":"136","author":"X Peng","year":"2015","unstructured":"Peng, X., Huang, J., Hu, Q., Zhang, S., Elgammal, A., & Metaxas, D. (2015a). From circle to 3-sphere: Head pose estimation by instance parameterization. Computer Vision and Image Understanding, 136, 92\u2013102.","journal-title":"Computer Vision and Image Understanding"},{"key":"1095_CR39","doi-asserted-by":"crossref","unstructured":"Peng, X., Yu, X., Sohn, K., Metaxas, D. N., & Chandraker, M. (2017a). Reconstruction-based disentanglement for pose-invariant face recognition. In Proceedings of the IEEE international conference on computer vision (pp. 1623\u20131632).","DOI":"10.1109\/ICCV.2017.180"},{"key":"1095_CR40","doi-asserted-by":"crossref","unstructured":"Peng, X., Zhang, S., Yang, Y., & Metaxas, D. N. (2015b). Piefa: Personalized incremental and ensemble face alignment. In: Proceedings of the IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2015.442"},{"key":"1095_CR41","first-page":"1","volume":"126","author":"X Peng","year":"2017","unstructured":"Peng, X., Zhang, S., Yu, Y., & Metaxas, D. N. (2017b). Toward personalized modeling: Incremental and ensemble alignment for sequential faces in the wild. International Journal of Computer Vision, 126, 1\u201314.","journal-title":"International Journal of Computer Vision"},{"key":"1095_CR42","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.imavis.2016.01.002","volume":"47","author":"C Sagonas","year":"2016","unstructured":"Sagonas, C., Antonakos, E., Tzimiropoulos, G., Zafeiriou, S., & Pantic, M. (2016). 300 faces in-the-wild challenge: database and results. Image and Vision Computing, 47, 3\u201318.","journal-title":"Image and Vision Computing"},{"key":"1095_CR43","doi-asserted-by":"crossref","unstructured":"Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., & Pantic, M. (2013). 300 faces in-the-wild challenge: The first facial landmark localization challenge. In Proceedings of the IEEE international conference on computer vision workshop.","DOI":"10.1109\/ICCVW.2013.59"},{"key":"1095_CR44","unstructured":"Schroff, F., Kalenichenko, D., & Philbin, J. (2015). Facenet: A unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 815\u2013823)."},{"key":"1095_CR45","doi-asserted-by":"crossref","unstructured":"Shen, J., Zafeiriou, S., Chrysos, G., Kossaifi, J., Tzimiropoulos, G., & Pantic, M. (2015). The first facial landmark tracking in-the-wild challenge: Benchmark and results. In Proceedings of the IEEE international conference on computer vision workshop.","DOI":"10.1109\/ICCVW.2015.132"},{"key":"1095_CR46","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. CoRR arXiv:1409.1556 ."},{"key":"1095_CR47","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, X., & Tang, X. (2013). Deep convolutional network cascade for facial point detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3476\u20133483).","DOI":"10.1109\/CVPR.2013.446"},{"key":"1095_CR48","unstructured":"Sun, Y., Wang, X., & Tang, X. (2015). Deeply learned face representations are sparse, selective, and robust. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2892\u20132900)."},{"key":"1095_CR49","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014). Deepface: Closing the gap to human-level performance in face verification. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2014.220"},{"key":"1095_CR50","doi-asserted-by":"crossref","unstructured":"Tzimiropoulos, G. (2015). Project-out cascaded regression with an application to face alignment. In CVPR (pp. 3659\u20133667).","DOI":"10.1109\/CVPR.2015.7298989"},{"key":"1095_CR51","doi-asserted-by":"crossref","unstructured":"Veeriah, V., Zhuang, N., & Qi, G. J. (2015) Differential recurrent neural networks for action recognition. In: Proceedings of the IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2015.460"},{"key":"1095_CR52","unstructured":"Wang, J., Cheng, Y., & Feris, R. S. (2016). Walk and learn: Facial attribute representation learning from egocentric video and contextual data. In: Proceedings of the IEEE conference on computer vision and pattern recognition."},{"issue":"10","key":"1095_CR53","doi-asserted-by":"publisher","first-page":"2071","DOI":"10.1109\/TPAMI.2015.2389830","volume":"37","author":"X Wang","year":"2015","unstructured":"Wang, X., Yang, M., Zhu, S., & Lin, Y. (2015). Regionlets for generic object detection. TPAMI, 37(10), 2071\u20132084.","journal-title":"TPAMI"},{"key":"1095_CR54","doi-asserted-by":"crossref","unstructured":"Wu, Y., & Ji, Q. (2016). Constrained joint cascade regression framework for simultaneous facial action unit recognition and facial landmark detection. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.370"},{"key":"1095_CR55","doi-asserted-by":"crossref","unstructured":"Xiong, X., & De la Torre, F. (2013). Supervised descent method and its application to face alignment. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2013.75"},{"key":"1095_CR56","unstructured":"Yang, J., Reed, S., Yang, M. H., & Lee, H. (2015). Weakly-supervised disentangling with recurrent transformations for 3D view synthesis. In NIPS."},{"key":"1095_CR57","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., & Courville, A. (2015) Describing videos by exploiting temporal structure. In Proceedings of the IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2015.512"},{"key":"1095_CR58","doi-asserted-by":"crossref","unstructured":"Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In European conference on computer vision (pp. 818\u2013833).","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"1095_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, J., Shan, S., Kan, M., & Chen, X. (2014a). Coarse-to-fine auto-encoder networks (CFAN) for real-time face alignment. In European conference on computer vision (pp. 1\u201316).","DOI":"10.1007\/978-3-319-10605-2_1"},{"key":"1095_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Luo, P., Loy, C. C., & Tang, X. (2014b). Facial landmark detection by deep multi-task learning. In European conference on computer vision (pp. 94\u2013108).","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"1095_CR61","unstructured":"Zhu, S., Li, C., Loy, C. C., & Tang, X. (2015). Face alignment by coarse-to-fine shape searching. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4998\u20135006)."},{"key":"1095_CR62","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 Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.23"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-018-1095-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-018-1095-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-018-1095-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,24]],"date-time":"2022-08-24T01:43:42Z","timestamp":1661305422000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-018-1095-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,23]]},"references-count":62,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2018,10]]}},"alternative-id":["1095"],"URL":"https:\/\/doi.org\/10.1007\/s11263-018-1095-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,23]]},"assertion":[{"value":"19 April 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}