{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T21:55:09Z","timestamp":1793051709816,"version":"4.5.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012694","type":"print"},{"value":"9783030012700","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\/978-3-030-01270-0_46","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T22:07:51Z","timestamp":1538777271000},"page":"781-797","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":81,"title":["ContextVP: Fully Context-Aware Video Prediction"],"prefix":"10.1007","author":[{"given":"Wonmin","family":"Byeon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rupesh Kumar","family":"Srivastava","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petros","family":"Koumoutsakos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"46_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"46_CR2","first-page":"575","volume":"4","author":"P Baldi","year":"2003","unstructured":"Baldi, P., Pollastri, G.: The principled design of large-scale recursive neural network architectures-dag-rnns and the protein structure prediction problem. J. Mach. Learn. Res. 4, 575\u2013602 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"46_CR3","doi-asserted-by":"crossref","unstructured":"Byeon, W., Breuel, T.M., Raue, F., Liwicki, M.: Scene labeling with lstm recurrent neural networks. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298977"},{"key":"46_CR4","doi-asserted-by":"crossref","unstructured":"Byeon, W., Liwicki, M., Breuel, T.M.: Texture classification using 2d lstm networks. In: 2014 22nd International Conference on Pattern Recognition (ICPR), pp. 1144\u20131149. IEEE (2014)","DOI":"10.1109\/ICPR.2014.206"},{"key":"46_CR5","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 304\u2013311. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"46_CR6","unstructured":"Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: Advances in Neural Information Processing Systems, pp. 64\u201372 (2016)"},{"issue":"11","key":"46_CR7","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"46_CR8","first-page":"249","volume":"9","author":"X Glorot","year":"2010","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. Aistats 9, 249\u2013256 (2010)","journal-title":"Aistats"},{"key":"46_CR9","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"46_CR10","first-page":"549","volume-title":"Lecture Notes in Computer Science","author":"Alex Graves","year":"2007","unstructured":"Graves, A., Fern\u00e1ndez, S., Schmidhuber, J.: Multi-dimensional recurrent neural networks. In: Proceedings of the 17th International Conference on Artificial Neural Networks, September 2007"},{"key":"46_CR11","unstructured":"Graves, A., Schmidhuber, J.: Offline handwriting recognition with multidimensional recurrent neural networks. In: NIPS (2009)"},{"key":"46_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-540-74690-4_56","volume-title":"Artificial Neural Networks \u2013 ICANN 2007","author":"A Graves","year":"2007","unstructured":"Graves, A., Fern\u00e1ndez, S., Schmidhuber, J.: Multi-dimensional recurrent neural networks. In: de S\u00e1, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds.) ICANN 2007. LNCS, vol. 4668, pp. 549\u2013558. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74690-4_56"},{"issue":"8","key":"46_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."},{"issue":"7","key":"46_CR14","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7","key":"46_CR15","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2014","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans.n Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2014)","journal-title":"IEEE Trans.n Pattern Anal. Mach. Intell."},{"key":"46_CR16","unstructured":"Kalchbrenner, N., et al.: Video pixel networks. arXiv preprint arXiv:1610.00527 (2016)"},{"key":"46_CR17","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"46_CR18","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"46_CR19","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Dai, W., Xing, E.P.: Dual motion gan for future-flow embedded video prediction. arXiv preprint arXiv:1708.00284 (2017)","DOI":"10.1109\/ICCV.2017.194"},{"key":"46_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yeh, R., Tang, X., Liu, Y., Agarwala, A.: Video frame synthesis using deep voxel flow. arXiv preprint arXiv:1702.02463 (2017)","DOI":"10.1109\/ICCV.2017.478"},{"key":"46_CR21","unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. arXiv preprint arXiv:1605.08104 (2016)"},{"key":"46_CR22","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. arXiv preprint arXiv:1511.05440 (2015)"},{"key":"46_CR23","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp. 807\u2013814 (2010)"},{"key":"46_CR24","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.: Action-conditional video prediction using deep networks in atari games. In: Advances in Neural Information Processing Systems, pp. 2863\u20132871 (2015)"},{"key":"46_CR25","unstructured":"Patraucean, V., Handa, A., Cipolla, R.: Spatio-temporal video autoencoder with differentiable memory. arXiv preprint arXiv:1511.06309 (2015)"},{"key":"46_CR26","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 arXiv:1412.6604 (2014)"},{"key":"46_CR27","doi-asserted-by":"crossref","unstructured":"Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: EpicFlow: edge-preserving interpolation of correspondences for optical flow. In: Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"46_CR28","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568\u2013576 (2014)"},{"key":"46_CR29","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"key":"46_CR30","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using lstms. In: International Conference on Machine Learning, pp. 843\u2013852 (2015)"},{"key":"46_CR31","unstructured":"Stollenga, M.F., Byeon, W., Liwicki, M., Schmidhuber, J.: Parallel multi-dimensional lstm, with application to fast biomedical volumetric image segmentation. In: Advances in Neural Information Processing Systems, pp. 2998\u20133006 (2015)"},{"key":"46_CR32","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"46_CR33","unstructured":"Tran, D., Bourdev, L.D., Fergus, R., Torresani, L., Paluri, M.: C3d: generic features for video analysis. CoRR, abs\/1412.0767 2, 7 (2014)"},{"key":"46_CR34","unstructured":"Villegas, R., et al.: Decomposing motion and content for natural video sequence prediction. In: ICLR (2017)"},{"key":"46_CR35","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Advances in Neural Information Processing Systems, pp. 613\u2013621 (2016)"},{"key":"46_CR36","unstructured":"Wang, Y., Long, M., Wang, J., Gao, Z., Philip, S.Y.: Predrnn: recurrent neural networks for predictive learning using spatiotemporal lstms. In: Advances in Neural Information Processing Systems, pp. 879\u2013888 (2017)"},{"issue":"4","key":"46_CR37","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"46_CR38","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: Advances in Neural Information Processing Systems, pp. 802\u2013810 (2015)"},{"key":"46_CR39","unstructured":"Xue, T., Wu, J., Bouman, K., Freeman, B.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2016)"},{"key":"46_CR40","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"}],"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\/978-3-030-01270-0_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:56:39Z","timestamp":1665017799000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01270-0_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012694","9783030012700"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01270-0_46","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"}]}}