{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T18:35:38Z","timestamp":1790188538255,"version":"4.1.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012274","type":"print"},{"value":"9783030012281","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\/978-3-030-01228-1_28","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T05:03:51Z","timestamp":1538802231000},"page":"466-483","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["Probabilistic Video Generation Using Holistic Attribute Control"],"prefix":"10.1007","author":[{"given":"Jiawei","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Lehrmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joseph","family":"Marino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Greg","family":"Mori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonid","family":"Sigal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Aubry, M., Maturana, D., Efros, A., Russell, B., Sivic, J.: Seeing 3D chairs: exemplar part-based 2D\u20133D alignment using a large dataset of CAD models. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.487"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as space-time shapes. In: ICCV (2005)","DOI":"10.1109\/ICCV.2005.28"},{"key":"28_CR3","doi-asserted-by":"crossref","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. ACM (2016)","DOI":"10.1145\/2812802"},{"key":"28_CR4","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)"},{"key":"28_CR5","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)"},{"key":"28_CR6","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: NIPS (2016)"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M., Yang, X., Kautz, J.: MoCoGAN: decomposing motion and content for video generation. CoRR (2017)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"28_CR8","unstructured":"Zhao, S., Song, J., Ermon, S.: Learning hierarchical features from deep generative models. In: ICML (2017)"},{"key":"28_CR9","unstructured":"Xue, T., Wu, J., Bouman, K., Freeman, B.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. In: NIPS (2016)"},{"key":"28_CR10","unstructured":"S\u00f8nderby, C.K., Raiko, T., Maal\u00f8e, L., S\u00f8nderby, S.K., Winther, O.: Ladder variational autoencoders. In: NIPS (2016)"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Serban, I.V., et al.: A hierarchical latent variable encoder-decoder model for generating dialogues. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.10983"},{"key":"28_CR12","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: NIPS (2016)"},{"key":"28_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-319-46493-0_47","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Yan","year":"2016","unstructured":"Yan, X., Yang, J., Sohn, K., Lee, H.: Attribute2Image: conditional image generation from visual attributes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 776\u2013791. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_47"},{"key":"28_CR14","unstructured":"Mathieu, M., Zhao, J., Sprechmann, P., Ramesh, A., LeCun, Y.: Disentangling factors of variation in deep representations using adversarial training. In: NIPS (2016)"},{"key":"28_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/978-3-319-46478-7_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Walker","year":"2016","unstructured":"Walker, J., Doersch, C., Gupta, A., Hebert, M.: An uncertain future: forecasting from static images using variational autoencoders. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 835\u2013851. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_51"},{"key":"28_CR16","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: NIPS (2016)"},{"key":"28_CR17","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1162\/089976600300015349","volume":"12","author":"J Tenenbaum","year":"2000","unstructured":"Tenenbaum, J., Freeman, W.: Separating style and content with bilinear models. Neural Comput. 12, 1247\u20131283 (2000)","journal-title":"Neural Comput."},{"key":"28_CR18","unstructured":"Elgammal, A., Lee, C.S.: Separating style and content on a nonlinear manifold. In: CVPR (2004)"},{"key":"28_CR19","unstructured":"Wang, J.M., Fleet, D.J., Hertzmann, A.: Gaussian process dynamical models. In: NIPS (2005)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Wang, J.M., Fleet, D.J., Hertzmann, A.: Multifactor Gaussian process models for style-content separation. In: ICML (2007)","DOI":"10.1145\/1273496.1273619"},{"key":"28_CR21","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: ICML (2014)"},{"key":"28_CR22","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: NIPS (2015)"},{"key":"28_CR23","unstructured":"Kingma, D.P., Mohamed, S., Rezende, D.J., Welling, M.: Semi-supervised learning with deep generative models. In: NIPS (2014)"},{"key":"28_CR24","unstructured":"Rezende, D.J., Mohamed, S.: Variational inference with normalizing flows. In: ICML (2015)"},{"key":"28_CR25","unstructured":"Kingma, D.P., Salimans, T., Jozefowicz, R., Chen, X., Sutskever, I., Welling, M.: Improving variational inference with inverse autoregressive flow. In: NIPS (2016)"},{"key":"28_CR26","unstructured":"Chung, J., Kastner, K., Dinh, L., Goel, K., Courville, A.C., Bengio, Y.: A recurrent latent variable model for sequential data. In: NIPS (2015)"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Matusik, W., Pfister, H., Brand, M., McMillan, L.: A Data-driven reflectance model. ACM ToG (2002)","DOI":"10.1145\/1201775.882343"},{"key":"28_CR28","unstructured":"Kulkarni, T.D., Whitney, W.F., Kohli, P., Tenenbaum, J.: Deep convolutional inverse graphics network. In: NIPS (2015)"},{"key":"28_CR29","unstructured":"Higgins, I., et al.: beta-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2017)"},{"key":"28_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/978-3-319-46484-8_16","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Zhou","year":"2016","unstructured":"Zhou, Y., Berg, T.L.: Learning temporal transformations from time-lapse videos. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 262\u2013277. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_16"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Lee, N., Choi, W., Vernaza, P., Choy, C.B., Torr, P.H.S., Chandraker, M.K.: DESIRE: distant future prediction in dynamic scenes with interacting agents. CoRR (2017)","DOI":"10.1109\/CVPR.2017.233"},{"key":"28_CR32","unstructured":"Krishnan, R.G., Shalit, U., Sontag, D.: Deep kalman filters. In: WS on Black Box Learning and Inference (2015)"},{"key":"28_CR33","unstructured":"Karl, M., Soelch, M., Bayer, J., van der Smagt, P.: Deep variational bayes filters: unsupervised learning of state space models from raw data. In: ICLR (2017)"},{"key":"28_CR34","unstructured":"Johnson, M., Duvenaud, D.K., Wiltschko, A., Adams, R.P., Datta, S.R.: Composing graphical models with neural networks for structured representations and fast inference. In: NIPS (2016)"},{"key":"28_CR35","unstructured":"Kalchbrenner, N., et al.: Video pixel networks. CoRR (2016)"},{"key":"28_CR36","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, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"28_CR37","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"28_CR38","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2014)"},{"key":"28_CR39","unstructured":"Yang, J., Reed, S.E., Yang, M.H., Lee, H.: Weakly-supervised disentangling with recurrent transformations for 3D view synthesis. In: NIPS (2015)"},{"key":"28_CR40","unstructured":"Salimans, T., et al.: Improved techniques for training GANs. In: NIPS (2016)"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"28_CR42","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O.: ImageNet large scale visual recognition challenge. IJCV 115, 211\u2013252 (2015)","journal-title":"IJCV"}],"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\/978-3-030-01228-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:29:01Z","timestamp":1665016141000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01228-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012274","9783030012281"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01228-1_28","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":"6 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"}]}}