{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:22:00Z","timestamp":1772907720364,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012234","name":"Shenzhen Peacock Plan","doi-asserted-by":"publisher","award":["20130408-183003656"],"award-info":[{"award-number":["20130408-183003656"]}],"id":[{"id":"10.13039\/501100012234","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Laboratory for Intelligent Multimedia and Virtual Reality","award":["ZDSYS-201703031405467"],"award-info":[{"award-number":["ZDSYS-201703031405467"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U-1613209"],"award-info":[{"award-number":["U-1613209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/tcsvt.2018.2882061","type":"journal-article","created":{"date-parts":[[2018,11,20]],"date-time":"2018-11-20T01:02:16Z","timestamp":1542675736000},"page":"3531-3543","source":"Crossref","is-referenced-by-count":12,"title":["Predicting Diverse Future Frames With Local Transformation-Guided Masking"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9464-4426","authenticated-orcid":false,"given":"Jinzhuo","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2664-4413","authenticated-orcid":false,"given":"Wenmin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_51"},{"key":"ref38","author":"yang","year":"2017","journal-title":"Lr-gan Layered recursive generative adversarial networks for image generation"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.291"},{"key":"ref32","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc NIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298744"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.194"},{"key":"ref37","author":"dumoulin","year":"2016","journal-title":"Adversarially learned inference"},{"key":"ref36","author":"donahue","year":"2016","journal-title":"Adversarial feature learning"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126737"},{"key":"ref34","author":"van amersfoort","year":"2017","journal-title":"Transformation-based models of video sequences"},{"key":"ref28","author":"sedaghat","year":"2016","journal-title":"Next-flow Hybrid multi-tasking with next-frame prediction to boost optical-flow estimation in the wild"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref29","author":"patraucean","year":"2015","journal-title":"Spatio-temporal video autoencoder with differentiable memory"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532921"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2270402"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123349"},{"key":"ref22","first-page":"1925","article-title":"Modeling deep temporal dependencies with recurrent grammar cells","author":"michalski","year":"2014","journal-title":"Proc NIPS"},{"key":"ref21","first-page":"1601","article-title":"The recurrent temporal restricted Boltzmann machine","author":"sutskever","year":"2009","journal-title":"Proc NIPS"},{"key":"ref24","first-page":"613","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"2016","journal-title":"Proc NIPS"},{"key":"ref23","first-page":"1647","article-title":"Structured recurrent temporal restricted Boltzmann machines","author":"mittelman","year":"2014","journal-title":"Proc ICML"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305029"},{"key":"ref25","first-page":"91","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","author":"xue","year":"2016","journal-title":"Proc NIPS"},{"key":"ref50","author":"abadi","year":"2016","journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref55","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"xingjian","year":"2015","journal-title":"Proc NIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"ref52","first-page":"25","article-title":"High accuracy optical flow estimation based on a theory for warping","author":"brox","year":"2004","journal-title":"Proc ECCV"},{"key":"ref10","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"2016","journal-title":"Proc NIPS"},{"key":"ref11","author":"lotter","year":"2016","journal-title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning"},{"key":"ref40","first-page":"346","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","author":"he","year":"2014","journal-title":"Proc ECCV"},{"key":"ref12","author":"villegas","year":"2017","journal-title":"Decomposing motion and content for natural video sequence prediction"},{"key":"ref13","author":"mathieu","year":"2015","journal-title":"Deep multi-scale video prediction beyond mean square error"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.281"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref16","author":"ranzato","year":"2014","journal-title":"Video (language) modeling a baseline for generative models of natural videos"},{"key":"ref17","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in atari games","author":"oh","year":"2015","journal-title":"Proc NIPS"},{"key":"ref18","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc ICML"},{"key":"ref19","author":"villegas","year":"2017","journal-title":"Learning to generate long-term future via hierarchical prediction"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"ref3","first-page":"811","article-title":"Deep alternative neural network: Exploring contexts as early as possible for action recognition","author":"wang","year":"2016","journal-title":"Proc NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019335"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64698-5_8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2855081"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2017.8050638"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref9","first-page":"1234","article-title":"Learning to linearize under uncertainty","author":"goroshin","year":"2015","journal-title":"Proc NIPS"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.10.018"},{"key":"ref45","author":"soomro","year":"2012","journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"ref42","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc NIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2813971"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref43","author":"rezende","year":"2016","journal-title":"One-shot generalization in deep generative models"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/8926550\/08540055.pdf?arnumber=8540055","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:56:33Z","timestamp":1657745793000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8540055\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":55,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2018.2882061","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12]]}}}