{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:19:56Z","timestamp":1781021996372,"version":"3.54.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,1]],"date-time":"2020-10-01T00:00:00Z","timestamp":1601510400000},"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":["61876095"],"award-info":[{"award-number":["61876095"]}],"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":["61751308"],"award-info":[{"award-number":["61751308"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Academy of Artificial Intelligence"},{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["51625503"],"award-info":[{"award-number":["51625503"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1109\/tmm.2019.2960700","type":"journal-article","created":{"date-parts":[[2019,12,18]],"date-time":"2019-12-18T20:53:22Z","timestamp":1576702402000},"page":"2551-2563","source":"Crossref","is-referenced-by-count":23,"title":["Deep Gesture Video Generation With Learning on Regions of Interest"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4737-788X","authenticated-orcid":false,"given":"Runpeng","family":"Cui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weishen","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8088-367X","authenticated-orcid":false,"given":"Changshui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4363-6108","authenticated-orcid":false,"given":"Jianqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref33","first-page":"406","article-title":"Pose guided person image generation","author":"ma","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01059"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.194"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref36","first-page":"1144","article-title":"Video-to-video synthesis","author":"wang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00870"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00359"},{"key":"ref28","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in Atari games","author":"oh","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.388"},{"key":"ref29","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"2017","journal-title":"arXiv 1706 08033"},{"key":"ref2","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref20","article-title":"Am I done? Predicting action progress in videos","author":"becattini","year":"2017","journal-title":"arXiv 1705 01781"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771448"},{"key":"ref21","first-page":"1911","article-title":"Extensions of the sign language recognition and translation corpus RWTH-PHOENIX-Weather","author":"forster","year":"0","journal-title":"Proc Int Conf Lang Resour Eval"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.281"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.416"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_51"},{"key":"ref25","first-page":"172","article-title":"Dèjá vu: Motion prediction in static images","author":"pintea","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2889563"},{"key":"ref51","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref52","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"unterthiner","year":"2018","journal-title":"arXiv 1812 01717"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47873-6_14"},{"key":"ref11","first-page":"236","article-title":"CSLDS: Chinese sign language dialog system","author":"chen","year":"0","journal-title":"Proc Int Workshop Anal Model Faces Gestures"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/EURCON.2005.1629959"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1090785.1090835"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23974-8_13"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_23"},{"key":"ref17","first-page":"2230","article-title":"Video prediction with appearance and motion conditions","author":"jang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_24"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.112"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref6","article-title":"Deep multi-scale video prediction beyond mean square error","author":"mathieu","year":"0","journal-title":"arXiv 1511 05440"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2771462"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.361"},{"key":"ref7","first-page":"613","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref49","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47873-6_15"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref45","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc Int Conf Med Image Comput Comput Assisted Intervention"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref47","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00059"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9204776\/08936484.pdf?arnumber=8936484","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:56:42Z","timestamp":1651075002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8936484\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10]]},"references-count":53,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2960700","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10]]}}}