{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T10:15:25Z","timestamp":1742984125835,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030033972"},{"type":"electronic","value":"9783030033989"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-03398-9_38","type":"book-chapter","created":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T13:12:41Z","timestamp":1541077961000},"page":"439-452","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Augmented Coarse-to-Fine Video Frame Synthesis with Semantic Loss"],"prefix":"10.1007","author":[{"given":"Xin","family":"Jin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8525-5066","authenticated-orcid":false,"given":"Zhibo","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Sen","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,11,2]]},"reference":[{"unstructured":"Abu-El-Haija, S., et al.: Youtube-8m: a large-scale video classification benchmark (2016). arXiv preprint: arXiv:1609.08675","key":"38_CR1"},{"issue":"4","key":"38_CR2","first-page":"39","volume":"5","author":"S Choudhary","year":"2016","unstructured":"Choudhary, S., Varshney, P.: A study of digital video compression techniques. PARIPEX-Indian J. Res. 5(4), 39\u201341 (2016)","journal-title":"PARIPEX-Indian J. Res."},{"key":"38_CR3","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1038\/377731a0","volume":"377","author":"P De Weerd","year":"1995","unstructured":"De Weerd, P., Gattass, R., Desimone, R., Ungerleider, L.G.: Responses of cells in monkey visual cortex during perceptual filling-in of an artificial scotoma. Nature 377, 731\u2013734 (1995)","journal-title":"Nature"},{"unstructured":"Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: NIPS, pp. 64\u201372 (2016)","key":"38_CR4"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","key":"38_CR5","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"38_CR6","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1152\/jn.00997.2007","volume":"100","author":"X Huang","year":"2008","unstructured":"Huang, X., Paradiso, M.A.: V1 response timing and surface filling-in. J. Neurophysiol. 100(1), 539\u2013547 (2008)","journal-title":"J. Neurophysiol."},{"unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization (2014). arXiv preprint: arXiv:1412.6980","key":"38_CR7"},{"key":"38_CR8","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1007\/978-3-642-33374-3_41","volume-title":"High Performance Computing in Science and Engineering 2012","author":"H Kuehne","year":"2013","unstructured":"Kuehne, H., Jhuang, H., Stiefelhagen, R., Serre, T.: HMDB51: a large video database for human motion recognition. In: Nagel, W., Kr\u00f6ner, D., Resch, M. (eds.) High Performance Computing in Science and Engineering 2012, pp. 571\u2013582. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-33374-3_41"},{"doi-asserted-by":"crossref","unstructured":"Li, S., Yeung, D.Y.: Visual object tracking for unmanned aerial vehicles: a benchmark and new motion models. In: AAAI, pp. 4140\u20134146 (2017)","key":"38_CR9","DOI":"10.1609\/aaai.v31i1.11205"},{"key":"38_CR10","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.neucom.2016.04.064","volume":"220","author":"W Li","year":"2017","unstructured":"Li, W., Cosker, D.: Video interpolation using optical flow and laplacian smoothness. Neurocomputing 220, 236\u2013243 (2017)","journal-title":"Neurocomputing"},{"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)","key":"38_CR11","DOI":"10.1109\/ICCV.2017.194"},{"doi-asserted-by":"crossref","unstructured":"Liu, Z., Yeh, R., Tang, X., Liu, Y., Agarwala, A.: Video frame synthesis using deep voxel flow. In: ICCV, vol. 2 (2017)","key":"38_CR12","DOI":"10.1109\/ICCV.2017.478"},{"unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. In: ICLR (2017)","key":"38_CR13"},{"doi-asserted-by":"crossref","unstructured":"Lu, C., Hirsch, M., Sch\u00f6lkopf, B.: Flexible spatio-temporal networks for video prediction. In: CVPR, pp. 6523\u20136531 (2017)","key":"38_CR14","DOI":"10.1109\/CVPR.2017.230"},{"unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: ICLR (2016)","key":"38_CR15"},{"doi-asserted-by":"crossref","unstructured":"Meyer, S., Wang, O., Zimmer, H., Grosse, M., Sorkine-Hornung, A.: Phase-based frame interpolation for video. In: CVPR, pp. 1410\u20131418 (2015)","key":"38_CR16","DOI":"10.1109\/CVPR.2015.7298747"},{"unstructured":"Michalski, V., Memisevic, R., Konda, K.: Modeling deep temporal dependencies with recurrent grammar cells. In: NIPS, pp. 1925\u20131933 (2014)","key":"38_CR17"},{"unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML 2010) (2010)","key":"38_CR18"},{"doi-asserted-by":"crossref","unstructured":"Niklaus, S., Mai, L., Liu, F.: Video frame interpolation via adaptive convolution. In: CVPR, vol. 2, p. 6 (2017)","key":"38_CR19","DOI":"10.1109\/CVPR.2017.244"},{"unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)","key":"38_CR20"},{"doi-asserted-by":"crossref","unstructured":"Ren, Z., Yan, J., Ni, B., Liu, B., Yang, X., Zha, H.: Unsupervised deep learning for optical flow estimation. In: AAAI, pp. 1495\u20131501 (2017)","key":"38_CR21","DOI":"10.1609\/aaai.v31i1.10723"},{"doi-asserted-by":"crossref","unstructured":"Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Epicflow: edge-preserving interpolation of correspondences for optical flow. In: CVPR, pp. 1164\u20131172 (2015)","key":"38_CR22","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"38_CR23","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, Part III. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"unstructured":"Soomro, K., Zamir, A.R., Shah, M.: Ucf101: a dataset of 101 human actions classes from videos in the wild (2012). arXiv preprint: arXiv:1212.0402","key":"38_CR24"},{"unstructured":"Villegas, R., Yang, J., Hong, S., Lin, X., Lee, H.: Decomposing motion and content for natural video sequence prediction. In: ICLR, vol. 1(2), p. 7 (2017)","key":"38_CR25"},{"unstructured":"Wang, Y., Long, M., Wang, J., Gao, Z., Philip, S.Y.: PredRNN: recurrent neural networks for predictive learning using spatiotemporal LSTMs. In: NIPS, pp. 879\u2013888 (2017)","key":"38_CR26"},{"unstructured":"Xue, T., Wu, J., Bouman, K., Freeman, B.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. In: NIPS, pp. 91\u201399 (2016)","key":"38_CR27"},{"unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions (2015). arXiv preprint: arXiv:1511.07122","key":"38_CR28"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03398-9_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T01:21:04Z","timestamp":1698801664000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-03398-9_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030033972","9783030033989"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03398-9_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"2 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"23 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/prcv.qyhw.net.cn\/?lang=en&meeting_id=255","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"}]}}