{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T23:30:02Z","timestamp":1769815802500,"version":"3.49.0"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012335","type":"print"},{"value":"9783030012342","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\/978-3-030-01234-2_44","type":"book-chapter","created":{"date-parts":[[2018,10,5]],"date-time":"2018-10-05T16:13:11Z","timestamp":1538755991000},"page":"747-763","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":79,"title":["SDC-Net: Video Prediction Using Spatially-Displaced Convolution"],"prefix":"10.1007","author":[{"given":"Fitsum A.","family":"Reda","sequence":"first","affiliation":[]},{"given":"Guilin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Kevin J.","family":"Shih","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Kirby","sequence":"additional","affiliation":[]},{"given":"Jon","family":"Barker","sequence":"additional","affiliation":[]},{"given":"David","family":"Tarjan","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Tao","sequence":"additional","affiliation":[]},{"given":"Bryan","family":"Catanzaro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"44_CR1","unstructured":"Abu-El-Haija, S., et al.: YouTube-8M: a large-scale video classification benchmark. arXiv preprint arXiv:1609.08675 (2016)"},{"key":"44_CR2","unstructured":"Babaeizadeh, M., Finn, C., Erhan, D., Campbell, R.H., Levine, S.: Stochastic variational video prediction. arXiv preprint arXiv:1710.11252 (2017)"},{"key":"44_CR3","doi-asserted-by":"crossref","unstructured":"Byeon, W., Wang, Q., Srivastava, R.K., Koumoutsakos, P.: Fully context-aware video prediction. arXiv preprint arXiv:1710.08518 (2017)","DOI":"10.1007\/978-3-030-01270-0_46"},{"key":"44_CR4","unstructured":"Denton, E., Fergus, R.: Stochastic video generation with a learned prior. arXiv preprint arXiv:1802.07687 (2018)"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: CVPR, June 2009","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. PAMI 34 (2012)","DOI":"10.1109\/TPAMI.2011.155"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: FlowNet 2.0: evolution of optical flow estimation with deep networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, H., Sun, D., Jampani, V., Yang, M.H., Learned-Miller, E., Kautz, J.: Super SloMo: high quality estimation of multiple intermediate frames for video interpolation. arXiv preprint arXiv:1712.00080 (2017)","DOI":"10.1109\/CVPR.2018.00938"},{"key":"44_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"44_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"44_CR13","unstructured":"Leibfried, F., Kushman, N., Hofmann, K.: A deep learning approach for joint video frame and reward prediction in Atari games. arXiv preprint arXiv:1611.07078 (2016)"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Dai, W., Xing, E.P.: Dual motion gan for future-flow embedded video prediction. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.194"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yeh, R., Tang, X., Liu, Y., Agarwala, A.: Video frame synthesis using deep voxel flow. In: International Conference on Computer Vision (ICCV), vol. 2 (2017)","DOI":"10.1109\/ICCV.2017.478"},{"key":"44_CR16","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"44_CR17","unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. In: ICLR (2014)"},{"key":"44_CR18","doi-asserted-by":"crossref","unstructured":"Lu, C., Hirsch, M., Sch\u00f6lkopf, B.: Flexible spatio-temporal networks for video prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6523\u20136531 (2017)","DOI":"10.1109\/CVPR.2017.230"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Luc, P., Neverova, N., Couprie, C., Verbeek, J., LeCun, Y.: Predicting deeper into the future of semantic segmentation. In: Proceedings of International Conference on Computer Vision, ICCV 2017, p. 10 (2017)","DOI":"10.1109\/ICCV.2017.77"},{"key":"44_CR20","doi-asserted-by":"crossref","unstructured":"Mahjourian, R., Wicke, M., Angelova, A.: Geometry-based next frame prediction from monocular video. In: 2017 IEEE Intelligent Vehicles Symposium (IV), pp. 1700\u20131707. IEEE (2017)","DOI":"10.1109\/IVS.2017.7995953"},{"key":"44_CR21","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: International Conference on Learning Representations (2016)"},{"key":"44_CR22","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"44_CR23","doi-asserted-by":"crossref","unstructured":"Niklaus, S., Mai, L., Liu, F.: Video frame interpolation via adaptive convolution. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.244"},{"key":"44_CR24","doi-asserted-by":"crossref","unstructured":"Niklaus, S., Mai, L., Liu, F.: Video frame interpolation via adaptive separable convolution. In: IEEE International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.37"},{"key":"44_CR25","doi-asserted-by":"publisher","unstructured":"Odena, A., Dumoulin, V., Olah, C.: Deconvolution and checkerboard artifacts. Distill (2016). https:\/\/doi.org\/10.23915\/distill.00003. http:\/\/distill.pub\/2016\/deconv-checkerboard","DOI":"10.23915\/distill.00003"},{"key":"44_CR26","doi-asserted-by":"crossref","unstructured":"Oliu, M., Selva, J., Escalera, S.: Folded recurrent neural networks for future video prediction. arXiv preprint arXiv:1712.00311 (2017)","DOI":"10.1007\/978-3-030-01264-9_44"},{"key":"44_CR27","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch (2017)"},{"key":"44_CR28","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":"44_CR29","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":"44_CR30","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556 (2014)"},{"key":"44_CR31","unstructured":"Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. In: ICML (2015)"},{"key":"44_CR32","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. arXiv preprint arXiv:1709.02371 (2017)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"44_CR33","unstructured":"Van Amersfoort, J., Kannan, A., Ranzato, M., Szlam, A., Tran, D., Chintala, S.: Transformation-based models of video sequences. arXiv preprint arXiv:1701.08435 (2017)"},{"key":"44_CR34","unstructured":"Villegas, R., Yang, J., Hong, S., Lin, X., Lee, H.: Decomposing motion and content for natural video sequence prediction. In: ICLR (2017)"},{"key":"44_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":"44_CR36","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Torralba, A.: Generating the future with adversarial transformers. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2992\u20133000 (2017)","DOI":"10.1109\/CVPR.2017.319"},{"key":"44_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1007\/978-3-319-68560-1_13","volume-title":"Image Analysis and Processing - ICIAP 2017","author":"V Vukoti\u0107","year":"2017","unstructured":"Vukoti\u0107, V., Pintea, S.-L., Raymond, C., Gravier, G., van Gemert, J.C.: One-step time-dependent future video frame prediction with a convolutional encoder-decoder neural network. In: Battiato, S., Gallo, G., Schettini, R., Stanco, F. (eds.) ICIAP 2017. LNCS, vol. 10484, pp. 140\u2013151. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-68560-1_13"},{"issue":"4","key":"44_CR38","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."}],"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\/978-3-030-01234-2_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,5]],"date-time":"2022-10-05T00:30:58Z","timestamp":1664929858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01234-2_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012335","9783030012342"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01234-2_44","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"}]}}