{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T07:44:31Z","timestamp":1759563871008,"version":"3.37.3"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["61836011","U20A20183","62021001"],"award-info":[{"award-number":["61836011","U20A20183","62021001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["2018497"],"award-info":[{"award-number":["2018497"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GPU"},{"name":"MCC Lab of Information Science and Technology Institution"},{"DOI":"10.13039\/501100009076","name":"University of Science and Technology of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009076","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3160297","type":"journal-article","created":{"date-parts":[[2022,3,19]],"date-time":"2022-03-19T01:37:14Z","timestamp":1647653834000},"page":"3397-3408","source":"Crossref","is-referenced-by-count":3,"title":["Coherent Image Animation Using Spatial-Temporal Correspondence"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0037-4147","authenticated-orcid":false,"given":"Weilun","family":"Wang","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of Technology in GIPAS, The Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in GIPAS, The Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"given":"Jianmin","family":"Bao","sequence":"additional","affiliation":[{"name":"Microsoft Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in GIPAS, The Department of Electrical Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2897897"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.194"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2963621"},{"article-title":"Conditional generative adversarial nets","year":"2014","author":"mirza","key":"ref10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01448"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01334-x"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_37"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref45","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"khurram soomro","year":"2012","journal-title":"CRCV-TR-12-01"},{"article-title":"In defense of the triplet loss for person re-identification","year":"2017","author":"hermans","key":"ref48"},{"key":"ref47","article-title":"OpenFace: A general-purpose face recognition library with mobile applications","volume":"6","author":"amos","year":"2016","journal-title":"CMU School of Computer Science"},{"key":"ref42","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref44","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","author":"finn","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","first-page":"2616","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"0","journal-title":"Proc Int Speech Commun Assoc"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref8","article-title":"CCVS: Context-aware controllable video synthesis","author":"moing","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00531"},{"key":"ref9","article-title":"V3GAN: Decomposing background, foreground and motion for video generation","author":"keshari","year":"2021","journal-title":"Brit Mach Vis Conf"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref3","first-page":"2849","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"0","journal-title":"IEEE Int Conf on Computer Vis (ICCV)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11881"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940684"},{"key":"ref35","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878970"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref30","first-page":"1144","article-title":"Video-to-video synthesis","author":"wang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2020.3031581"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref1","first-page":"7137","article-title":"First order motion model for image animation","author":"siarohin","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_13"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011290"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00316"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00600"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2960700"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240704"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref27","article-title":"LARNet: Latent action representation for human action synthesis","author":"biyani","year":"2021","journal-title":"Brit Mach Vis Conf"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09738544.pdf?arnumber=9738544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:00:33Z","timestamp":1693245633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9738544\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3160297","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2023]]}}}