{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:33:36Z","timestamp":1778081616004,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,11]]},"DOI":"10.1109\/dicta.2017.8227441","type":"proceedings-article","created":{"date-parts":[[2017,12,22]],"date-time":"2017-12-22T01:19:08Z","timestamp":1513905548000},"page":"1-8","source":"Crossref","is-referenced-by-count":32,"title":["Human Pose Forecasting via Deep Markov Models"],"prefix":"10.1109","author":[{"given":"Sam","family":"Toyer","sequence":"first","affiliation":[]},{"given":"Anoop","family":"Cherian","sequence":"additional","affiliation":[]},{"given":"Tengda","family":"Han","sequence":"additional","affiliation":[]},{"given":"Stephen","family":"Gould","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"A recurrent latent variable model for sequential data","author":"chung","year":"2015","journal-title":"NIPS"},{"key":"ref38","author":"bayer","year":"2014","journal-title":"Learning stochastic recurrent networks"},{"key":"ref33","author":"mahjourian","year":"2016","journal-title":"Geometry-based next frame prediction from monocular video"},{"key":"ref32","author":"mathieu","year":"2015","journal-title":"Deep multi-scale video prediction beyond mean square error"},{"key":"ref31","author":"vondrick","year":"2016","journal-title":"Generating videos with scene dynamics"},{"key":"ref30","article-title":"An uncertain future: Forecasting from static images using variational autoencoders","author":"walker","year":"2016","journal-title":"ECCV"},{"key":"ref37","author":"doersch","year":"2016","journal-title":"Tutorial on variational autoencoders"},{"key":"ref36","author":"rezende","year":"2014","journal-title":"Stochastic backpropagation and approximate inference in deep generative models"},{"key":"ref35","author":"kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref34","author":"finn","year":"2016","journal-title":"Unsupervised learning for physical interaction through video prediction"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref40","article-title":"Sequential neural models with stochastic layers","author":"fraccaro","year":"2016","journal-title":"NIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"ref12","article-title":"Learning spatio-temporal structure from RGB-D videos for human activity detection and anticipation","author":"koppula","year":"2013","journal-title":"ICML"},{"key":"ref13","article-title":"Action-reaction: Forecasting the dynamics of human interaction","author":"huang","year":"2014","journal-title":"ECCV"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2017.01.011","article-title":"Space-time representation of people based on 3D skeletal data: A review","author":"han","year":"2017","journal-title":"Computer Vision and Image Understanding"},{"key":"ref15","article-title":"Modeling human motion using binary latent variables","author":"taylor","year":"2006","journal-title":"NIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref17","author":"krishnan","year":"2016","journal-title":"Structured inference networks for nonlinear state space models"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"ref28","article-title":"Déja vu","author":"pintea","year":"2014","journal-title":"ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.334"},{"key":"ref27","article-title":"On human motion prediction using recurrent neural networks","author":"martinez","year":"2017","journal-title":"CVPR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298664"},{"key":"ref6","author":"cao","year":"2016","journal-title":"Realtime multi-person 2d pose estimation using part affinity fields"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.281"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.222"},{"key":"ref8","article-title":"Multi-person pose estimation with local joint-to-person associations","author":"iqbal","year":"2016","journal-title":"ECCV"},{"key":"ref7","article-title":"Deepercut: A deeper, stronger, and faster multi-person pose estimation model","author":"insafutdinov","year":"2016","journal-title":"ECCV"},{"key":"ref2","author":"newell","year":"2016","journal-title":"Stacked Hourglass Networks for Human Pose Estimation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.494"},{"key":"ref1","author":"wei","year":"2016","journal-title":"Convolutional pose machines"},{"key":"ref20","article-title":"Articulated pose estimation by a graphical model with image dependent pairwise relations","author":"chen","year":"2014","journal-title":"NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref21","article-title":"Conditional regression forests for human pose estimation","author":"sun","year":"2012","journal-title":"CVPR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1167"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0859-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.302"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0524-9"},{"key":"ref26","article-title":"The recurrent temporal restricted boltzmann machine","author":"sutskever","year":"2008","journal-title":"NIPS"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref25","article-title":"Learning switching linear models of human motion","author":"pavlovic","year":"2000","journal-title":"NIPS"}],"event":{"name":"2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","location":"Sydney, NSW","start":{"date-parts":[[2017,11,29]]},"end":{"date-parts":[[2017,12,1]]}},"container-title":["2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8226656\/8227375\/08227441.pdf?arnumber=8227441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T23:10:23Z","timestamp":1643152223000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8227441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/dicta.2017.8227441","relation":{},"subject":[],"published":{"date-parts":[[2017,11]]}}}