{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:43:14Z","timestamp":1783744994720,"version":"3.55.0"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2019R1C1C1010249"],"award-info":[{"award-number":["NRF-2019R1C1C1010249"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and communications Technology Planning and Evaluation","award":["2018-0-00765"],"award-info":[{"award-number":["2018-0-00765"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3035281","type":"journal-article","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T21:04:46Z","timestamp":1604351086000},"page":"3986-3998","source":"Crossref","is-referenced-by-count":21,"title":["Dynamic Motion Estimation and Evolution Video Prediction Network"],"prefix":"10.1109","volume":"23","author":[{"given":"Nayoung","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1637-9479","authenticated-orcid":false,"given":"Je-Won","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"A note on the inception score","author":"barratt","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_14"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref30","first-page":"6038","article-title":"Hierarchical long-term video prediction without supervision","author":"wichers","year":"2018","journal-title":"Proc"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2946475"},{"key":"ref36","first-page":"667","article-title":"Dynamic filter networks","author":"jia","year":"2016","journal-title":"Advances Neural Inform Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_44"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.37"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825100"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2449078"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2861567"},{"key":"ref2","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","year":"2015","journal-title":"Proc 7th Int Conf Machine Learning"},{"key":"ref1","article-title":"Learning to generate long-term future via hierarchical prediction","year":"0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2960700"},{"key":"ref22","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","year":"2012"},{"key":"ref21","first-page":"4450","article-title":"View extrapolation of human body from a single image","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref24","first-page":"971","article-title":"ActionVLAD: Learning spatio-temporal aggregation for action classification","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref23","article-title":"YouTube-8M: A large-scale video classification benchmark","year":"0","journal-title":"arXiv 1609 08675"},{"key":"ref26","article-title":"Learnable pooling with context gating for video classification","year":"0","journal-title":"arXiv 1706 06905"},{"key":"ref25","first-page":"6047","article-title":"AVA: A video dataset of spatio-temporally localized atomic visual actions","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref50","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref10","article-title":"Folded recurrent neural networks for future video prediction","year":"0","journal-title":"arXiv 1712 00311"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-30157-5_76"},{"key":"ref11","first-page":"1744","article-title":"Dual motion gan for future-flow embedded video prediction","volume":"1","year":"2017","journal-title":"Proc"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2903455"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","year":"0","journal-title":"arXiv 1409 1556"},{"key":"ref15","first-page":"3578","article-title":"Long-term video generation with evolving residual video frames","year":"0","journal-title":"Proc 25th IEEE Int Conf Image Process"},{"key":"ref16","first-page":"170","article-title":"DYAN: A dynamical atoms-based network for video prediction","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","year":"0","journal-title":"Adv Neural Inf Process Sys"},{"key":"ref18","first-page":"3521","article-title":"Newtonian scene understanding: Unfolding the dynamics of objects in static images","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2983567"},{"key":"ref4","first-page":"1460","article-title":"Structure preserving video prediction","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref3","article-title":"Decomposing motion and content for natural video sequence prediction","year":"2017","journal-title":"arXiv 1706 08033"},{"key":"ref6","first-page":"4414","article-title":"Unsupervised learning of disentangled representations from video","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.230"},{"key":"ref8","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","year":"0","journal-title":"Advances Neural Inf Process Syst"},{"key":"ref7","article-title":"Deep multi-scale video prediction beyond mean square error","year":"0","journal-title":"arXiv 1511 05440"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref9","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","year":"0","journal-title":"arXiv 1605 08104"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2011.645783"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-741252-8.50010-8"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref42","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00003"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09246714.pdf?arnumber=9246714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:36Z","timestamp":1652194296000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9246714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3035281","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}