{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:38:17Z","timestamp":1774600697821,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2015,7,1]],"date-time":"2015-07-01T00:00:00Z","timestamp":1435708800000},"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":[[2015,7,1]]},"DOI":"10.1109\/tpami.2014.2368990","type":"journal-article","created":{"date-parts":[[2014,11,10]],"date-time":"2014-11-10T19:36:58Z","timestamp":1415648218000},"page":"1425-1441","source":"Crossref","is-referenced-by-count":8,"title":["A Framework for Efficient Structured Max-Margin Learning of High-Order MRF Models"],"prefix":"10.1109","volume":"37","author":[{"given":"Nikos","family":"Komodakis","sequence":"first","affiliation":[]},{"given":"Bo","family":"Xiang","sequence":"additional","affiliation":[]},{"given":"Nikos","family":"Paragios","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33709-3_15"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126242"},{"key":"ref33","first-page":"57","article-title":"Stacked hierarchical labeling","author":"munoz","year":"0","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref32","first-page":"779","article-title":"Max-margin min-entropy models","author":"miller","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref31","first-page":"783","article-title":"Learning efficiently with approximate inference via dual losses","author":"meshi","year":"0","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref30","first-page":"1594","article-title":"Direct loss minimization for structured prediction","author":"mcallester","year":"0","journal-title":"Proc Adv Neural Inform Process Syst 23"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126429"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623499362111"},{"key":"ref35","first-page":"467","article-title":"Loopy-belief propagation for approximate inference: An empirical study","author":"murphy","year":"0","journal-title":"Proc 15th Conf Uncertainty Artif Intell"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206590"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553523"},{"key":"ref28","author":"li","year":"2009","journal-title":"Markov Random Field Modeling in Image Analysis"},{"key":"ref27","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"0","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587699"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.133"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126227"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408890"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206846"},{"key":"ref24","first-page":"465","article-title":"Modeling latent variable uncertainty for loss-based learning","author":"kumar","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.108"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-7007-9"},{"key":"ref25","first-page":"153","article-title":"Exploiting inference for approximate parameter learning in discriminative fields: An empirical study","author":"kumar","year":"0","journal-title":"Proc 5th Int Conf Energy Minimization Methods Comput Vis Pattern Recognit"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587669"},{"key":"ref51","first-page":"21","article-title":"Randomized optimum models for structured prediction","author":"tarlow","year":"0","journal-title":"Proc 15th Conf Artif Intell Statist"},{"key":"ref59","first-page":"316","article-title":"DivMCuts: Faster training of structural SVMs with diverse m-best cutting-planes","author":"yadollahpour","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2012.6235836"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2011.5872733"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2012.6235836"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1036"},{"key":"ref54","first-page":"92","article-title":"Discriminative learning with latent variables for cluttered indoor scene understanding","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref53","article-title":"Max-margin Markov networks","author":"taskar","year":"0","journal-title":"Proc Neural Inform Process Syst"},{"key":"ref52","first-page":"1212","article-title":"Structured output learning with high order loss functions","author":"tarlow","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref40","first-page":"886","article-title":"Learning low-order models for enforcing high-order statistics","author":"pletscher","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390195"},{"key":"ref12","first-page":"67","article-title":"Discriminative learning of max-sum classifiers","volume":"9","author":"franc","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref13","article-title":"Max-margin learning for lower linear envelope potentials in binary MRFs","author":"gould","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.233"},{"key":"ref15","first-page":"838","article-title":"A primal-dual message-passing algorithm for approximated large scale structured prediction","author":"hazan","year":"0","journal-title":"Proc Adv Neural Inform Process Syst 23"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.175"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383204"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995375"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/64.3.616"},{"key":"ref3","author":"bertsekas","year":"1999","journal-title":"Nonlinear Programming"},{"key":"ref6","author":"censor","year":"0","journal-title":"Parallel Optimization Theory Algorithms and Applications"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/8579.001.0001","author":"blake","year":"2011","journal-title":"Advances in Markov Random Fields for Vision and Image Processing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1995.1004"},{"key":"ref49","first-page":"582","article-title":"Learning CRFs using graph cuts","author":"szummer","year":"0","journal-title":"Proc 10th Eur Conf Comput Vis"},{"key":"ref7","first-page":"109","article-title":"Approximation algorithms for the metric labeling problem via a new linear programming formulation","author":"chekuri","year":"0","journal-title":"Proc 12th Annu ACM-SIAM Symp Discrete Algorithms"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.31"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0420-4"},{"key":"ref45","first-page":"959","article-title":"Efficient structured prediction with latent variables for general graphical models","author":"schwing","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70844"},{"key":"ref47","first-page":"2181","article-title":"More data means less inference: A pseudo-max approach to structured learning","author":"sontag","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206774"},{"key":"ref41","article-title":"(Online) subgradient methods for structured prediction","author":"ratliff","year":"0","journal-title":"Proc 11th Int Conf Artif Intell Statist"},{"key":"ref44","article-title":"Solution to structural recognition (MAX,+)-problems by their equivalent transformations","author":"schlesinger","year":"2007","journal-title":"Control Syst Comput"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383191"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7116666\/06951487.pdf?arnumber=6951487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:05:10Z","timestamp":1642003510000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6951487\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,1]]},"references-count":60,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2014.2368990","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,7,1]]}}}