{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:04:29Z","timestamp":1772553869320,"version":"3.50.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012663","type":"print"},{"value":"9783030012670","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01267-0_24","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T17:02:36Z","timestamp":1538845356000},"page":"403-419","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":59,"title":["Learning to Forecast and Refine Residual Motion for Image-to-Video Generation"],"prefix":"10.1007","author":[{"given":"Long","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Xi","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Mubbasir","family":"Kapadia","sequence":"additional","affiliation":[]},{"given":"Dimitris","family":"Metaxas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,7]]},"reference":[{"key":"24_CR1","unstructured":"Aifanti, N., Papachristou, C., Delopoulos, A.: The MUG facial expression database. In: International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) (2010)"},{"key":"24_CR2","unstructured":"Amos, B., Ludwiczuk, B., Satyanarayanan, M.: OpenFace: a general-purpose face recognition library with mobile applications. Technical report, CMU-CS-16-118, CMU School of Computer Science (2016)"},{"key":"24_CR3","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning (ICML) (2017)"},{"issue":"9","key":"24_CR4","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1109\/TPAMI.2003.1227983","volume":"25","author":"V Blanz","year":"2003","unstructured":"Blanz, V., Vetter, T.: Face recognition based on fitting a 3D morphable model. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 25(9), 1063\u20131074 (2003)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Yang, J., Price, B., Cohen, S., Deng, J.: Forecasting human dynamics from static images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.388"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: IEEE International Conference on Computer Vision (ICCV), pp. 4346\u20134354 (2015)","DOI":"10.1109\/ICCV.2015.494"},{"key":"24_CR7","unstructured":"Goodfellow, I. et al.: Generative adversarial nets. In: Annual Conference on Neural Information Processing Systems (NIPS), pp. 2672\u20132680 (2014)"},{"key":"24_CR8","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of wasserstein GANs. In: Annual Conference on Neural Information Processing Systems (NIPS) (2017)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, S., van der Maaten, L., Weinberger, K.Q.: Condensenet: an efficient densenet using learned group convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00291"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.243"},{"issue":"1","key":"24_CR11","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"24_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2014)"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Laine, S. et al.: Production-level facial performance capture using deep convolutional neural networks. In: Proceedings of the ACM SIGGRAPH\/Eurographics Symposium on Computer Animation (2017)","DOI":"10.1145\/3099564.3099581"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yeh, R.A., Tang, X., Liu, Y., Agarwala, A.: Video frame synthesis using deep voxel flow. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.478"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Lu, J., Issaranon, T., Forsyth, D.: SafetyNet: detecting and rejecting adversarial examples robustly. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.56"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. In: Annual Conference on Neural Information Processing Systems (NIPS), pp. 405\u2013415 (2017)","DOI":"10.1109\/CVPR.2018.00018"},{"key":"24_CR17","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"24_CR18","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"24_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-3-319-46484-8_29","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Newell","year":"2016","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483\u2013499. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_29"},{"key":"24_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Olszewski, K. et al.: Realistic dynamic facial textures from a single image using GANs. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.580"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Paysan, P., Knothe, R., Amberg, B., Romdhani, S., Vetter, T.: A 3D face model for pose and illumination invariant face recognition. In: IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS) for Security, Safety and Monitoring in Smart Environments (2009)","DOI":"10.1109\/AVSS.2009.58"},{"key":"24_CR23","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-319-46448-0_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Xi Peng","year":"2016","unstructured":"Peng, X., Feris, R.S., Wang, X., Metaxas, D.N.: A recurrent encoder-decoder network for sequential face alignment. In: European Conference on Computer Vision (ECCV), pp. 38\u201356 (2016)"},{"key":"24_CR24","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.: From circle to 3-sphere: head pose estimation by instance parameterization. Comput. Vis. Image Underst. (CVIU) 136, 92\u2013102 (2015)","journal-title":"Comput. Vis. Image Underst. (CVIU)"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Peng, X., Tang, Z., Yang, F., Feris, R.S., Metaxas, D.: Jointly optimize data augmentation and network training: Adversarial data augmentation in human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2226\u20132234 (2018)","DOI":"10.1109\/CVPR.2018.00237"},{"key":"24_CR26","unstructured":"Perarnau, G., van de Weijer, J., Raducanu, B., \u00c1lvarez, J.M.: Invertible conditional GANs for image editing. In: NIPS Workshop on Adversarial Training (2016)"},{"key":"24_CR27","unstructured":"Reed, S.E., Zhang, Y., Zhang, Y., Lee, H.: Deep visual analogy-making. In: Annual Conference on Neural Information Processing Systems (NIPS) (2015)"},{"key":"24_CR28","doi-asserted-by":"crossref","unstructured":"Shen, W., Liu, R.: Learning residual images for face attribute manipulation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.135"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.241"},{"key":"24_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)"},{"key":"24_CR31","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Annual Conference on Neural Information Processing Systems (NIPS), pp. 568\u2013576 (2014)"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Tang, Z., Peng, X., Geng, S., Wu, L., Zhang, S., Metaxas, D.N.: Quantized densely connected U-Nets for efficient landmark localization. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01219-9_21"},{"key":"24_CR33","unstructured":"Tang, Z., Peng, X., Geng, S., Zhu, Y., Metaxas, D.: CU-Net: coupled U-Nets. In: British Machine Vision Conference (BMVC) (2018)"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Thies, J., Zollh\u00f6fer, M., Stamminger, M., Theobalt, C., Nie\u00dfner, M.: Face2Face: real-time face capture and reenactment of RGB videos. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.262"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Tian, Y., Peng, X., Zhao, L., Zhang, S., Metaxas, D.N.: CR-GAN: learning complete representations for multi-view generation. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 942\u2013948 (2018)","DOI":"10.24963\/ijcai.2018\/131"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: IEEE International Conference on Computer Vision (ICCV), pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: MoCoGAN: decomposing motion and content for video generation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"24_CR38","unstructured":"Villegas, R., Yang, J., Hong, S., Lin, X., Lee, H.: Decomposing motion and content for natural video sequence prediction. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"24_CR39","unstructured":"Villegas, R., Yang, J., Zou, Y., Sohn, S., Lin, X., Lee, H.: Learning to generate long-term future via hierarchical prediction. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"24_CR40","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Annual Conference on Neural Information Processing Systems (NIPS) (2016)"},{"key":"24_CR41","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.c.: Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In: Annual Conference on Neural Information Processing Systems (NIPS), pp. 802\u2013810 (2015)"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Xiong, W., Luo, W., Ma, L., Liu, W., Luo, J.: Learning to generate time-lapse videos using multi-stage dynamic generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00251"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, H. et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"24_CR44","unstructured":"Zhang, H., Sindagi, V., Patel, V.M.: Image de-raining using a conditional generative adversarial network. arXiv preprint arXiv:1701.05957 (2017)"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, W., Zhu, M., Derpanis, K.: From Actemes to action: a strongly-supervised representation for detailed action understanding. In: IEEE International Conference on Computer Vision (ICCV) (2013)","DOI":"10.1109\/ICCV.2013.280"},{"key":"24_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Xie, Y., Yang, L.: Photographic text-to-image synthesis with a hierarchically-nested adversarial network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00649"},{"key":"24_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Yang, L., Zheng, Y.: Translating and segmenting multimodal medical volumes with cycle-and shapeconsistency generative adversarial network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00963"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Zhu, X., Lei, Z., Liu, X., Shi, H., Li, S.: Face alignment across large poses: A 3D solution. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.23"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01267-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:17:55Z","timestamp":1665015475000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01267-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012663","9783030012670"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01267-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.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"}]}}