{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T17:00:48Z","timestamp":1790960448548,"version":"4.1.0"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464473","type":"print"},{"value":"9783319464480","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46448-0_3","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T08:27:24Z","timestamp":1474014444000},"page":"38-56","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":86,"title":["A Recurrent Encoder-Decoder Network for Sequential Face Alignment"],"prefix":"10.1007","author":[{"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":[[2016,9,17]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Asthana, A., Zafeiriou, S., Cheng, S., Pantic, M.: Incremental face alignment in the wild. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.240"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Asthana, A., Zafeiriou, S., Cheng, S., Pantic, M.: Robust discriminative response map fitting with constrained local models. In: CVPR, pp. 3444\u20133451 (2013)","DOI":"10.1109\/CVPR.2013.442"},{"key":"3_CR3","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. CoRR (2015)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Belhumeur, P.N., Jacobs, D.W., Kriegman, D.J., Kumar, N.: Localizing parts of faces using a consensus of exemplars. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995602"},{"key":"3_CR5","unstructured":"Black, M., Yacoob, Y.: Tracking and recognizing rigid and non-rigid facial motions using local parametric models of image motion. In: CVPR, pp. 374\u2013381 (1995)"},{"issue":"2","key":"3_CR6","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.: Face alignment by explicit shape regression. IJCV 107(2), 177\u2013190 (2014)","journal-title":"IJCV"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. CoRR abs\/1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Chrysos, G.G., Antonakos, E., Zafeiriou, S., Snape, P.: Offline deformable face tracking in arbitrary videos. In: ICCVW, pp. 954\u2013962 (2015)","DOI":"10.1109\/ICCVW.2015.126"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Cootes, T.F., Taylor, C.J.: Active shape models-smart snakes. In: BMVC (1992)","DOI":"10.5244\/C.6.28"},{"issue":"2","key":"3_CR10","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1023\/A:1008122917811","volume":"38","author":"D Decarlo","year":"2000","unstructured":"Decarlo, D., Metaxas, D.: Optical flow constraints on deformable models with applications to face tracking. IJCV 38(2), 99\u2013127 (2000)","journal-title":"IJCV"},{"key":"3_CR11","unstructured":"FGNet: talking face video. Technical report (2004). http:\/\/www-prima.inrialpes.fr\/FGnet\/data\/01-TalkingFace\/talking_face.html"},{"issue":"2","key":"3_CR12","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.: A review of active appearance models. IEEE Trans. Syst. Man Cybern. 40(2), 145\u2013158 (2010)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"issue":"8","key":"3_CR13","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.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"3_CR14","unstructured":"Hong, S., Noh, H., Han, B.: Decoupled deep neural network for semi-supervised semantic segmentation. CoRR abs\/1506.04924 (2015)"},{"key":"3_CR15","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR abs\/1502.03167 (2015)"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: ACMM, pp. 675\u2013678 (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Jourabloo, A., Liu, X.: Large-pose face alignment via cnn-based dense 3D model fitting. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.454"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR, June 2015","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"3_CR19","unstructured":"Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian segnet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. CoRR abs\/1511.02680 (2015)"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Koestinger, M., Wohlhart, P., Roth, P.M., Bischof, H.: Annotated facial landmarks in the wild: a large-scale, real-world database for facial landmark localization. In: Workshop on Benchmarking Facial Image Analysis Technologies (2011)","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"3_CR21","unstructured":"Lai, H., Xiao, S., Cui, Z., Pan, Y., Xu, C., Yan, S.: Deep cascaded regression for face alignment (2015). arXiv:1510.09083v2"},{"key":"3_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1007\/978-3-642-33712-3_49","volume-title":"Computer Vision\u2013ECCV 2012","author":"V Le","year":"2012","unstructured":"Le, V., Brandt, J., Lin, Z., Bourdev, L., Huang, T.S.: Interactive facial feature localization. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 679\u2013692. Springer, Heidelberg (2012). doi: 10.1007\/978-3-642-33712-3_49"},{"key":"3_CR23","unstructured":"Learned-Miller, G.: Labeled faces in the wild: updates and new reporting procedures. Technical report. UM-CS-2014-003, University of Massachusetts, Amherst (2014)"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. CoRR abs\/1411.4038 (2014)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"3_CR25","unstructured":"Long, J.L., Zhang, N., Darrell, T.: Do convnets learn correspondence? In: NIPS, pp. 1601\u20131609 (2014)"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Lu, L., Zhang, X., Cho, K., Renals, S.: A study of the recurrent neural network encoder-decoder for lar ge vocabulary speech recognition. In: INTERSPEECH (2015)","DOI":"10.1109\/ICASSP.2016.7472641"},{"key":"3_CR27","unstructured":"Mikolov, T., Joulin, A., Chopra, S., Mathieu, M., Ranzato, M.: Learning longer memory in recurrent neural networks. CoRR abs\/1412.7753 (2014)"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Mikolov, T., Karafi\u00e1t, M., Burget, L., Cernock\u00fd, J., Khudanpur, S.: Recurrent neural network based language model. In: INTERSPEECH, pp. 1045\u20131048 (2010)","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"3_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1007\/978-3-540-88693-8_37","volume-title":"Computer Vision\u2013ECCV 2008","author":"S Milborrow","year":"2008","unstructured":"Milborrow, S., Nicolls, F.: Locating facial features with an extended active shape model. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5305, pp. 504\u2013513. Springer, Heidelberg (2008). doi: 10.1007\/978-3-540-88693-8_37"},{"key":"3_CR30","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML, pp. 807\u2013814 (2010)"},{"key":"3_CR31","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.: Action-conditional video prediction using deep networks in atari games. In: NIPS, pp. 2845\u20132853 (2015)"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Oliver, N., Pentland, A., Berard, F.: Lafter: lips and face real time tracker. In: CVPR, pp. 123\u2013129 (1997)","DOI":"10.1109\/CVPR.1997.609309"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Patras, I., Pantic, M.: Particle filtering with factorized likelihoods for tracking facial features. In: Proceedings of Automatic Face and Gesture Recognition, pp. 97\u2013102 (2004)","DOI":"10.1109\/AFGR.2004.1301515"},{"key":"3_CR34","first-page":"92","volume":"136","author":"X Peng","year":"2015","unstructured":"Peng, X., Huang, J., Hu, Q., Zhang, S., Elgammal, A., Metaxas, D.: From circle to 3-sphere: head pose estimation by instance parameterization. CVIU 136, 92\u2013102 (2015)","journal-title":"CVIU"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Peng, X., Huang, J., Hu, Q., Zhang, S., Metaxas, D.N.: Three-dimensional head pose estimation in-the-wild. In: FG, vol. 1, pp. 1\u20136 (2015)","DOI":"10.1109\/FG.2015.7163109"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Peng, X., Zhang, S., Yang, Y., Metaxas, D.N.: Piefa: personalized incremental and ensemble face alignment. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.442"},{"key":"3_CR37","doi-asserted-by":"crossref","unstructured":"Sagonas, C., Tzimiropoulos, G., Zafeiriou, S., Pantic, M.: 300 faces in-the-wild challenge: the first facial landmark localization challenge. In: ICCVW (2013)","DOI":"10.1109\/ICCVW.2013.59"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: CVPR, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Shen, J., Zafeiriou, S., Chrysos, G., Kossaifi, J., Tzimiropoulos, G., Pantic, M.: The first facial landmark tracking in-the-wild challenge: benchmark and results. In: ICCVW (2015)","DOI":"10.1109\/ICCVW.2015.132"},{"key":"3_CR40","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, X., Tang, X.: Deep convolutional network cascade for facial point detection. In: CVPR, pp. 3476\u20133483 (2013)","DOI":"10.1109\/CVPR.2013.446"},{"key":"3_CR42","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, X., Tang, X.: Deeply learned face representations are sparse, selective, and robust. In: CVPR, pp. 2892\u20132900 (2015)","DOI":"10.1109\/CVPR.2015.7298907"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.220"},{"issue":"7","key":"3_CR44","first-page":"3273","volume":"21","author":"M Tang","year":"2012","unstructured":"Tang, M., Peng, X.: Robust tracking with discriminative ranking lists. TIP 21(7), 3273\u20133281 (2012)","journal-title":"TIP"},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Tzimiropoulos, G.: Project-out cascaded regression with an application to face alignment. In: CVPR, pp. 3659\u20133667 (2015)","DOI":"10.1109\/CVPR.2015.7298989"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Veeriah, V., Zhuang, N., Qi, G.J.: Differential recurrent neural networks for action recognition. In: ICCV, December 2015","DOI":"10.1109\/ICCV.2015.460"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Wang, J., Cheng, Y., Feris, R.S.: Walk and learn: facial attribute representation learning from egocentric video and contextual data. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.252"},{"issue":"10","key":"3_CR48","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.: Regionlets for generic object detection. TPAMI 37(10), 2071\u20132084 (2015)","journal-title":"TPAMI"},{"key":"3_CR49","doi-asserted-by":"crossref","unstructured":"Wu, Y., Ji, Q.: Constrained joint cascade regression framework for simultaneous facial action unit recognition and facial landmark detection. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.370"},{"key":"3_CR50","doi-asserted-by":"crossref","unstructured":"Xuehan-Xiong, D., la Torre, F.: Supervised descent method and its application to face alignment. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.75"},{"key":"3_CR51","unstructured":"Yang, J., Reed, S., Yang, M.H., Lee, H.: Weakly-supervised disentangling with recurrent transformations for 3D view synthesis. In: NIPS (2015)"},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., Courville, A.: Describing videos by exploiting temporal structure. In: ICCV, December 2015","DOI":"10.1109\/ICCV.2015.512"},{"key":"3_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision\u2013ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10590-1_53"},{"key":"3_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-10605-2_1","volume-title":"Computer Vision\u2013ECCV 2014","author":"J Zhang","year":"2014","unstructured":"Zhang, J., Shan, S., Kan, M., Chen, X.: Coarse-to-Fine Auto-Encoder Networks (CFAN) for real-time face alignment. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 1\u201316. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10605-2_1"},{"key":"3_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/978-3-319-10599-4_7","volume-title":"Computer Vision\u2013ECCV 2014","author":"Z Zhang","year":"2014","unstructured":"Zhang, Z., Luo, P., Loy, C.C., Tang, X.: Facial landmark detection by deep multi-task learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 94\u2013108. Springer, Heidelberg (2014). doi: 10.1007\/978-3-319-10599-4_7"},{"key":"3_CR56","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., Torr, P.H.S.: Conditional random fields as recurrent neural networks. In: ICCV, December 2015","DOI":"10.1109\/ICCV.2015.179"},{"key":"3_CR57","doi-asserted-by":"crossref","unstructured":"Zhu, S., Li, C., Loy, C.C., Tang, X.: Face alignment by coarse-to-fine shape searching. In: CVPR, pp. 4998\u20135006 (2015)","DOI":"10.1109\/CVPR.2015.7299134"},{"key":"3_CR58","doi-asserted-by":"crossref","unstructured":"Zhu, X., Lei, Z., Liu, X., Shi, H., Li, S.Z.: Face alignment across large poses: a 3D solution. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.23"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46448-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T19:14:20Z","timestamp":1749582860000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46448-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464473","9783319464480"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46448-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}