{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:28:48Z","timestamp":1781587728833,"version":"3.54.5"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464770","type":"print"},{"value":"9783319464787","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\/978-3-319-46478-7_51","type":"book-chapter","created":{"date-parts":[[2016,9,15]],"date-time":"2016-09-15T09:48:37Z","timestamp":1473932917000},"page":"835-851","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":228,"title":["An Uncertain Future: Forecasting from Static Images Using Variational Autoencoders"],"prefix":"10.1007","author":[{"given":"Jacob","family":"Walker","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carl","family":"Doersch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhinav","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martial","family":"Hebert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2016,9,16]]},"reference":[{"key":"51_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, P., Carreira, J., Malik, J.: Learning to see by moving. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.13"},{"issue":"1","key":"51_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-010-0390-2","volume":"92","author":"S Baker","year":"2011","unstructured":"Baker, S., Scharstein, D., Lewis, J., Roth, S., Black, M.J., Szeliski, R.: A database and evaluation methodology for optical flow. IJCV 92(1), 1\u201331 (2011)","journal-title":"IJCV"},{"key":"51_CR3","unstructured":"Doersch, C.: Tutorial on variational autoencoders. arXiv preprint (2016). \n                      arXiv:1606.05908"},{"key":"51_CR4","doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.167"},{"key":"51_CR5","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., van der Smagt, P., Cremers, D., Brox, T.: Flownet: learning optical flow with convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"51_CR6","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"51_CR7","doi-asserted-by":"crossref","unstructured":"Fouhey, D., Zitnick, C.L.: Predicting object dynamics in scenes. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.260"},{"key":"51_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"51_CR9","unstructured":"Gorban, A., Idrees, H., Jiang, Y.G., Roshan Zamir, A., Laptev, I., Shah, M., Sukthankar, R.: THUMOS challenge: action recognition with a large number of classes (2015). \n                      http:\/\/www.thumos.info\/"},{"key":"51_CR10","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D., Wierstra, D.: DRAW: a recurrent neural network for image generation. In: ICML (2015)"},{"issue":"2","key":"51_CR11","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/s11263-013-0683-3","volume":"107","author":"M Hoai","year":"2014","unstructured":"Hoai, M., De la Torre, F.: Max-margin early event detectors. IJCV 107(2), 191\u2013202 (2014)","journal-title":"IJCV"},{"key":"51_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/978-3-319-10584-0_32","volume-title":"Computer Vision \u2013 ECCV 2014","author":"D-A Huang","year":"2014","unstructured":"Huang, D.-A., Kitani, K.M.: Action-reaction: forecasting the dynamics of human interaction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 489\u2013504. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10584-0_32"},{"key":"51_CR13","unstructured":"Kingma, D.P., Mohamed, S., Rezende, D.J., Welling, M.: Semi-supervised learning with deep generative models. In: NIPS (2014)"},{"key":"51_CR14","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: ICLR (2014)"},{"key":"51_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/978-3-642-33765-9_15","volume-title":"Computer Vision \u2013 ECCV 2012","author":"KM Kitani","year":"2012","unstructured":"Kitani, K.M., Ziebart, B.D., Bagnell, J.A., Hebert, M.: Activity forecasting. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7575, pp. 201\u2013214. Springer, Heidelberg (2012). doi:\n                      10.1007\/978-3-642-33765-9_15"},{"key":"51_CR16","doi-asserted-by":"crossref","unstructured":"Koppula, H.S., Saxena, A.: Anticipating human activities using object affordances for reactive robotic response. In: RSS (2013)","DOI":"10.15607\/RSS.2013.IX.006"},{"key":"51_CR17","unstructured":"Kr\u00e4henb\u00fchl, P., Doersch, C., Donahue, J., Darrell, T.: Data-dependent initializations of convolutional neural networks. ICLR (2016)"},{"key":"51_CR18","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"51_CR19","unstructured":"Kulkarni, T., Whitney, W.F., Kohli, P., Tenenbaum, J.: Deep convolutional inverse graphics network. In: NIPS (2015)"},{"key":"51_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/978-3-319-10578-9_45","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T Lan","year":"2014","unstructured":"Lan, T., Chen, T.-C., Savarese, S.: A hierarchical representation for future action prediction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 689\u2013704. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10578-9_45"},{"issue":"5","key":"51_CR21","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1109\/TPAMI.2010.147","volume":"33","author":"C Liu","year":"2011","unstructured":"Liu, C., Yuen, J., Torralba, A.: Sift flow: dense correspondence across scenes and its applications. PAMI 33(5), 978\u2013994 (2011)","journal-title":"PAMI"},{"key":"51_CR22","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Bagherinezhad, H., Rastegari, M., Farhadi, A.: Newtonian image understanding: unfolding the dynamics of objects in static images. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.383"},{"key":"51_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-3-319-10578-9_12","volume-title":"Computer Vision \u2013 ECCV 2014","author":"SL Pintea","year":"2014","unstructured":"Pintea, S.L., Gemert, J.C., Smeulders, A.W.M.: D\u00e9j\u00e0 Vu: motion prediction in static images. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 172\u2013187. Springer, Heidelberg (2014). doi:\n                      10.1007\/978-3-319-10578-9_12"},{"key":"51_CR24","unstructured":"Ranzato, M., Szlam, A., Bruna, J., Mathieu, M., Collobert, R., Chopra, S.: Video (language) modeling: a baseline for generative models of natural videos. arXiv preprint (2014). \n                      arXiv:1412.6604"},{"key":"51_CR25","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: ICML (2014)"},{"key":"51_CR26","unstructured":"Salimans, T., Kingma, D., Welling, M.: Markov chain monte carlo and variational inference: bridging the gap. In: ICML (2015)"},{"key":"51_CR27","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint (2012). \n                      arXiv:1212.0402"},{"key":"51_CR28","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. In: ICML (2015)"},{"key":"51_CR29","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Anticipating the future by watching unlabeled video. In: CVPR (2016)"},{"key":"51_CR30","doi-asserted-by":"crossref","unstructured":"Walker, J., Gupta, A., Hebert, M.: Patch to the future: unsupervised visual prediction. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.416"},{"key":"51_CR31","doi-asserted-by":"crossref","unstructured":"Walker, J., Gupta, A., Hebert, M.: Dense optical flow prediction from a static image. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.281"},{"key":"51_CR32","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Unsupervised learning of visual representations using videos. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.320"},{"key":"51_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/978-3-642-15552-9_51","volume-title":"Computer Vision \u2013 ECCV 2010","author":"J Yuen","year":"2010","unstructured":"Yuen, J., Torralba, A.: A data-driven approach for event prediction. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6312, pp. 707\u2013720. Springer, Heidelberg (2010). doi:\n                      10.1007\/978-3-642-15552-9_51"}],"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\/978-3-319-46478-7_51","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T01:21:41Z","timestamp":1602292901000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46478-7_51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464770","9783319464787"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46478-7_51","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":"16 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"}]}}