{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:10:56Z","timestamp":1779379856476,"version":"3.53.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,1]],"date-time":"2023-05-01T00:00:00Z","timestamp":1682899200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100013348","name":"Innosuisse - Schweizerische Agentur f\u00fcr Innovationsf\u00f6rderung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Swiss Innovation Agency"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,5,1]]},"DOI":"10.1109\/tpami.2022.3215307","type":"journal-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T21:07:05Z","timestamp":1667509625000},"page":"6415-6427","source":"Crossref","is-referenced-by-count":16,"title":["Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8472-166X","authenticated-orcid":false,"given":"Sina","family":"Honari","sequence":"first","affiliation":[{"name":"CVLab, EPFL, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7825-9763","authenticated-orcid":false,"given":"Victor","family":"Constantin","sequence":"additional","affiliation":[{"name":"CVLab, EPFL, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2692-0801","authenticated-orcid":false,"given":"Helge","family":"Rhodin","sequence":"additional","affiliation":[{"name":"Imager Lab, UBC, Vancouver, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8347-8637","authenticated-orcid":false,"given":"Mathieu","family":"Salzmann","sequence":"additional","affiliation":[{"name":"CVLab, EPFL, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6702-9970","authenticated-orcid":false,"given":"Pascal","family":"Fua","sequence":"additional","affiliation":[{"name":"CVLab, EPFL, Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.138"},{"key":"ref4","first-page":"5242","article-title":"Self-supervised learning of motion capture","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tung"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00880"},{"key":"ref7","first-page":"7695","article-title":"Neural scene decomposition for human motion capture","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Rhodin"},{"key":"ref8","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref9","first-page":"3765","article-title":"Unsupervised feature extraction by time-contrastive learning and nonlinear ICA","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hyvarinen"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref11","first-page":"8769","article-title":"Unsupervised state representation learning in atari","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Anand"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462891"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.226"},{"key":"ref15","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Srivastava"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01058"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"ref22","article-title":"Learning from unlabelled videos using contrastive predictive neural 3D mapping","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Harley"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.348"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00285"},{"key":"ref25","article-title":"Self-supervised learning of a facial attribute embedding from video","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Wiles"},{"key":"ref26","first-page":"4020","article-title":"Unsupervised learning of object landmarks through conditional image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jakab"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00646"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01121"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00881"},{"key":"ref30","first-page":"9736","article-title":"Unsupervised depth estimation, 3D face rotation and replacement","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Moniz"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_46"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00694"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_13"},{"key":"ref35","first-page":"2615","article-title":"Isolating sources of disentanglement in variational autoencoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref37","first-page":"2180","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00531"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00608"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.611"},{"key":"ref41","first-page":"4414","article-title":"Unsupervised learning of disentangled representations from video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref42","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jaderberg"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126500"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/s19194323"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.467"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00586"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00744"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00797"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.01.103"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00234"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00529"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01309"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00619"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.288"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref58","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref60","article-title":"Adam: A method for stochastic optimisation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref61","first-page":"6389","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00866"},{"issue":"5","key":"ref63","article-title":"Weight, volume, and center of mass segments of the human body","volume":"13","author":"Clauser","year":"1971","journal-title":"J. Occup. Environ. Med."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10091695\/09921314.pdf?arnumber=9921314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:52:51Z","timestamp":1719345171000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9921314\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,1]]},"references-count":63,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3215307","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":[[2023,5,1]]}}}