{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T04:43:16Z","timestamp":1783744996734,"version":"3.55.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Engineering Laboratory for Video Technology - Shenzhen Division"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1613209"],"award-info":[{"award-number":["U1613209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Fund of Macau","award":["FDCT, 0016\/2019\/A1"],"award-info":[{"award-number":["FDCT, 0016\/2019\/A1"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1109\/tmm.2019.2946475","type":"journal-article","created":{"date-parts":[[2019,10,14]],"date-time":"2019-10-14T19:21:16Z","timestamp":1571080876000},"page":"1591-1604","source":"Crossref","is-referenced-by-count":16,"title":["Uni-and-Bi-Directional Video Prediction via Learning Object-Centric Transformation"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6349-8737","authenticated-orcid":false,"given":"Xiongtao","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2664-4413","authenticated-orcid":false,"given":"Wenmin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1771","article-title":"Video pixel networks","author":"kalchbrenner","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref38","article-title":"Stochastic variational video prediction","author":"babaeizadeh","year":"2017","journal-title":"arXiv 1710 11252"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68560-1_13"},{"key":"ref32","first-page":"613","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref31","first-page":"91","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","author":"xue","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref30","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"arXiv 1701 07875"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_51"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.319"},{"key":"ref35","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"xingjian","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref60","article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"arXiv 1212 0402"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.280"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref28","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.281"},{"key":"ref29","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"arXiv 1511 06434"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2758524"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15552-9_51"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.147"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126359"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_15"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298747"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0683-3"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"ref51","article-title":"One-shot generalization in deep generative models","author":"rezende","year":"2016","journal-title":"arXiv 1603 05106"},{"key":"ref59","author":"abadi","year":"2016","journal-title":"arXiv 1603 04467"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123349"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref55","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2014","journal-title":"Arxiv 1412 7755"},{"key":"ref54","first-page":"77","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"14","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref52","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2815784"},{"key":"ref11","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","first-page":"3560","article-title":"Learning to generate long-term future via hierarchical prediction","author":"villegas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"2015","journal-title":"arXiv 1511 05440"},{"key":"ref13","article-title":"Video (language) modeling: A baseline for generative models of natural videos","author":"ranzato","year":"2014","journal-title":"arXiv 1412 6604"},{"key":"ref14","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref15","first-page":"5515","article-title":"Deepstereo: Learning to predict new views from the world's imagery","author":"flynn","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit"},{"key":"ref16","article-title":"Spatio-temporal video autoencoder with differentiable memory","author":"patraucean","year":"2015","journal-title":"arXiv 1511 06309"},{"key":"ref17","first-page":"667","article-title":"Dynamic filter networks","author":"de brabandere","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref18","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.230"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/381"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2759504"},{"key":"ref6","first-page":"670","article-title":"Video frame interpolation via adaptive convolution","author":"niklaus","year":"0","journal-title":"Proc Comput Vision Pattern Recognit"},{"key":"ref5","article-title":"Video frame interpolation and extrapolation","author":"gong","year":"0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661277"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790301"},{"key":"ref46","article-title":"Transformation-based models of video sequences","author":"amersfoort","year":"2017","journal-title":"arXiv 1701 08435"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.194"},{"key":"ref48","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in atari games","author":"oh","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref41","first-page":"658","article-title":"Generating images with perceptual similarity metrics based on deep networks","author":"dosovitskiy","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_46"},{"key":"ref43","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"2017","journal-title":"arXiv 1706 08033"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9097818\/08868218.pdf?arnumber=8868218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:55:45Z","timestamp":1651074945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8868218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":63,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2946475","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}