{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:54:53Z","timestamp":1780764893692,"version":"3.54.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T00:00:00Z","timestamp":1617235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61751308"],"award-info":[{"award-number":["61751308"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61773311"],"award-info":[{"award-number":["61773311"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61603057"],"award-info":[{"award-number":["61603057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities, CHD","doi-asserted-by":"publisher","award":["300102320202"],"award-info":[{"award-number":["300102320202"]}],"id":[{"id":"10.13039\/501100012226","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":[[2021,4]]},"DOI":"10.1109\/tcsvt.2020.2984783","type":"journal-article","created":{"date-parts":[[2020,4,1]],"date-time":"2020-04-01T21:20:01Z","timestamp":1585776001000},"page":"1283-1295","source":"Crossref","is-referenced-by-count":45,"title":["Video Frame Prediction by Deep Multi-Branch Mask Network"],"prefix":"10.1109","volume":"31","author":[{"given":"Sen","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianwu","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongke","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianru","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.291"},{"key":"ref38","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00191"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.310"},{"key":"ref31","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","article-title":"Next-flow: Hybrid multi-tasking with next-frame prediction to boost optical-flow estimation in the wild","volume":"abs 1612 3777v2","author":"sedaghat","year":"2017","journal-title":"CoRR"},{"key":"ref37","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref36","first-page":"1","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.545"},{"key":"ref34","first-page":"515","article-title":"Learning to decompose and disentangle representations for video prediction","author":"hsieh","year":"2018","journal-title":"Proc NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.751"},{"key":"ref27","first-page":"434","article-title":"Learning image matching by simply watching video","author":"long","year":"2016","journal-title":"Proc ECCV"},{"key":"ref29","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"2016","journal-title":"Proc NIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913478447"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2013.6629564"},{"key":"ref20","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in atari games","author":"oh","year":"2015","journal-title":"Proc NIPS"},{"key":"ref22","first-page":"1","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"2017","journal-title":"Proc ICLR"},{"key":"ref21","article-title":"Video (language) modeling: A baseline for generative models of natural videos","volume":"abs 1412 6604v5","author":"ranzato","year":"2016","journal-title":"CoRR"},{"key":"ref24","article-title":"Unsupervised learning of visual structure using predictive generative networks","volume":"abs 1511 6380v2","author":"lotter","year":"2016","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref26","first-page":"835","article-title":"An uncertain future: Forecasting from static images using variational autoencoders","author":"walker","year":"2016","journal-title":"Proc ECCV"},{"key":"ref25","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","author":"xingjian","year":"2015","journal-title":"Proc NIPS"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.315"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.391"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2330853"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.45"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019325"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.86"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00803"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296547"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref11","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"2015","journal-title":"Proc ICML"},{"key":"ref40","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.194"},{"key":"ref13","first-page":"753","article-title":"ContextVP: Fully context-aware video prediction","author":"byeon","year":"2018","journal-title":"Proc ECCV"},{"key":"ref14","article-title":"Spatio-temporal video autoencoder with differentiable memory","volume":"abs 1511 6309v5","author":"patraucean","year":"2016","journal-title":"CoRR"},{"key":"ref15","first-page":"613","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"2016","journal-title":"Proc NIPS"},{"key":"ref16","first-page":"1","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"2016","journal-title":"Proc ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"ref18","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","volume":"abs 1212 402v1","author":"soomro","year":"2012","journal-title":"CoRR"},{"key":"ref19","first-page":"91","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","author":"xue","year":"2016","journal-title":"Proc NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-018-1126-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500419"},{"key":"ref6","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"lotter","year":"2017","journal-title":"Proc ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793523"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2882061"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2389511"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539872"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2800773"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref45","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc ICAIS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206569"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298720"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"ref41","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc MICCAI"},{"key":"ref44","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9394821\/09052726.pdf?arnumber=9052726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:20Z","timestamp":1652194220000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9052726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4]]},"references-count":58,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2020.2984783","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4]]}}}