{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:28:38Z","timestamp":1780586918693,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tpami.2021.3055560","type":"journal-article","created":{"date-parts":[[2021,1,29]],"date-time":"2021-01-29T21:21:42Z","timestamp":1611955302000},"page":"1-1","source":"Crossref","is-referenced-by-count":14,"title":["Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos"],"prefix":"10.1109","author":[{"given":"Aysegul","family":"Dundar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Shih","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Animesh","family":"Garg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Pottorff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bryan","family":"Catanzaro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stochastic variational video prediction","author":"Babaeizadeh","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00870"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5244\/C.27.47"},{"key":"ref4","first-page":"1174","article-title":"Stochastic video generation with a learned prior","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Denton"},{"key":"ref5","first-page":"4414","article-title":"Unsupervised learning of disentangled representations from video","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref6","first-page":"64","article-title":"Unsupervised learning for physical interaction through video prediction","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Finn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref8","first-page":"4020","article-title":"Unsupervised learning of object landmarks through conditional image generation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Jakab"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.354"},{"key":"ref10","first-page":"3809","article-title":"Unsupervised keypoint learning for guiding class-conditional video prediction","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref11","article-title":"Videoflow: A flow-based generative model for video","author":"Kumar","year":"2019"},{"key":"ref12","article-title":"Stochastic adversarial video prediction","author":"Lee","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01121"},{"key":"ref15","first-page":"406","article-title":"Pose guided person image generation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00018"},{"key":"ref17","article-title":"Spectral normalization for generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Miyato"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref19","first-page":"2863","article-title":"Action-conditional video prediction using deep networks in atari games","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Oh"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.222"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00098"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00789"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_46"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"ref28","article-title":"Video interpolation and prediction with unsupervised landmarks","author":"Shih","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00248"},{"key":"ref30","first-page":"7135","article-title":"First order motion model for image animation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Siarohin"},{"key":"ref31","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srivastava"},{"key":"ref32","first-page":"2059","article-title":"Discovery of latent 3D keypoints via end-to-end geometric reasoning","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Suwajanakorn"},{"key":"ref33","first-page":"844","article-title":"Unsupervised learning of object frames by dense equivariant image labelling","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Thewlis"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.348"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref36","first-page":"3560","article-title":"Learning to generate long-term future via hierarchical prediction","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Villegas"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.281"},{"key":"ref38","first-page":"6038","article-title":"Hierarchical long-term video prediction without supervision","author":"Villegas"},{"key":"ref39","first-page":"91","article-title":"Visual dynamics: Probabilistic future frame synthesis via cross convolutional networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Xue"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00285"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_24"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09340560.pdf?arnumber=9340560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:09:57Z","timestamp":1704841797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9340560\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3055560","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}