{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T22:32:10Z","timestamp":1777761130051,"version":"3.51.4"},"reference-count":104,"publisher":"Emerald","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,5,31]]},"abstract":"<jats:p>Computational visual perception seeks to reproduce human vision through the combination of visual sensors, artificial intelligence and computing. To this end, computer vision tasks are often reformulated as mathematical inference problems where the objective is to determine the set of parameters corresponding to the lowest potential of a taskspecific objective function. Graphical models have been the most popular formulation in the field over the past two decades where the problem is viewed as a discrete assignment labeling one. Modularity, scalability and portability are the main strengths of these methods which once combined with efficient inference algorithms they could lead to state of the art results. In this tutorial we focus on the inference component of the problem and in particular we discuss in a systematic manner the most commonly used optimization principles in the context of graphical models. Our study concerns inference over low rank models (interactions between variables are constrained to pairs) as well as higher order ones (arbitrary set of variables determine hyper-cliques on which constraints are introduced) and seeks a concise, self-contained presentation of prior art as well as the presentation of the current state of the art methods in the field.<\/jats:p>","DOI":"10.1561\/0600000066","type":"journal-article","created":{"date-parts":[[2016,5,31]],"date-time":"2016-05-31T11:17:35Z","timestamp":1464693455000},"page":"1-102","source":"Crossref","is-referenced-by-count":5,"title":["(Hyper)-Graphs Inference through Convex Relaxations and Move Making Algorithms: Contributions and Applications in Artificial Vision"],"prefix":"10.1108","volume":"10","author":[{"given":"Nikos","family":"Komodakis","sequence":"first","affiliation":[{"name":"Ecole des Ponts ParisTech University Paris Est, ,","place":["France"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. Pawan","family":"Kumar","sequence":"additional","affiliation":[{"name":"University of Oxford Department of Engineering Science, ,","place":["UK"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikos","family":"Paragios","sequence":"additional","affiliation":[{"name":"Universite Paris-Saclay CentraleSupelec, INRIA, ,","place":["France"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2016,5,31]]},"reference":[{"issue":"3","key":"2026032615264574400_ref001","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1109\/TIP.2010.2076294","article-title":"An augmented Lagrangian approach to the constrained optimization formulation of imaging inverse problems","volume":"20","author":"Afonso","year":"2011","journal-title":"IEEE Transactions on Image Processing"},{"key":"2026032615264574400_ref002","first-page":"1079","article-title":"Approximate classification via earthmover metrics","volume-title":"Proceedings of the ACM-SIAM Symposium on Discrete Algorithms","author":"Archer","year":"2004"},{"key":"2026032615264574400_ref003","first-page":"17","article-title":"Generic cuts: An efficient algorithm for optimal inference in higher order MRF-MAP","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Arora","year":"2012"},{"key":"2026032615264574400_ref004","first-page":"161","article-title":"On approximating arbitrary metrics by tree metrics","volume-title":"Proceedings of the Annual ACM Symposium on Theory of Computing","author":"Bartal","year":"1998"},{"key":"2026032615264574400_ref005","first-page":"1","article-title":"Diversem-best solutions in Markov random fields","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Batra","year":"2012"},{"key":"2026032615264574400_ref006","first-page":"1295","article-title":"Shape priors and discrete mrfs for knowledge-based segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Besbes","year":"2009"},{"key":"2026032615264574400_ref007","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/8579.001.0001","volume-title":"Markov Random Fields for Vision and Image Processing","author":"Blake","year":"2011"},{"issue":"9","key":"2026032615264574400_ref008","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.1109\/TPAMI.2004.60","article-title":"An experimental comparison of min-cut\/max-flow algorithms for energy minimization in vision","volume":"26","author":"Boykov","year":"2004","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"11","key":"2026032615264574400_ref009","doi-asserted-by":"crossref","first-page":"1222","DOI":"10.1109\/34.969114","article-title":"Fast approximate energy minimization via graph cuts","volume":"23","author":"Boykov","year":"2001","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"12","key":"2026032615264574400_ref010","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1109\/34.735802","article-title":"A variable window approach to early vision","volume":"20","author":"Boykov","year":"1998","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"6","key":"2026032615264574400_ref011","doi-asserted-by":"crossref","first-page":"3172","DOI":"10.1016\/j.aim.2012.08.008","article-title":"Hyperconvexity and tight-span theory for diversities","volume":"231","author":"Bryant","year":"2012","journal-title":"Advances in Mathematics"},{"key":"2026032615264574400_ref012","first-page":"109","article-title":"Approximation algorithms for the metric labeling problem via a new linear programming formulation","volume-title":"Proceedings of the ACM-SIAM Symposium on Discrete Algorithms","author":"Chekuri","year":"2001"},{"issue":"5","key":"2026032615264574400_ref013","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1109\/34.1000236","article-title":"Mean shift: A robust approach toward feature space analysis","volume":"24","author":"Comaniciu","year":"2002","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026032615264574400_ref014","first-page":"2105","article-title":"Inference by learning: Speeding-up graphical model optimization via a coarse-to-fine cascade of pruning classifiers","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Conejo","year":"2014"},{"key":"2026032615264574400_ref015","first-page":"2173","article-title":"Fast approximate energy minimization with label costs","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Delong","year":"2010"},{"issue":"1","key":"2026032615264574400_ref016","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/s11263-012-0531-x","article-title":"Minimizing energies with hierarchical costs","volume":"100","author":"Delong","year":"2012","journal-title":"International Journal of Computer Vision"},{"key":"2026032615264574400_ref017","first-page":"1760","article-title":"Parsimonious labeling","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Dokania","year":"2015"},{"key":"2026032615264574400_ref018","first-page":"448","article-title":"A tight bound on approximating arbitrary metrics by tree metrics","volume-title":"Proceedings of the Annual ACM Symposium on Theory of Computing","author":"Fakcharoenphol","year":"2003"},{"key":"2026032615264574400_ref019","first-page":"261","article-title":"Efficient belief propagation for early vision","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Felzenszwalb","year":"2004"},{"issue":"1","key":"2026032615264574400_ref020","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/T-C.1973.223602","article-title":"The representation and matching of pictorial structures","volume":"22","author":"Fischler","year":"1973","journal-title":"IEEE Transactions on Computers"},{"key":"2026032615264574400_ref021","first-page":"3104","article-title":"Structured learning of sum-of-submodular higher order energy functions","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Fix","year":"2013"},{"key":"2026032615264574400_ref022","first-page":"553","article-title":"A primal-dual method for higher-order multilabel Markov random fields","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Fix","year":"2014"},{"key":"2026032615264574400_ref023","volume-title":"Technical report","author":"Flach","year":"2006"},{"issue":"6","key":"2026032615264574400_ref024","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1109\/TPAMI.1984.4767596","article-title":"Stochastic relaxation, gibbs distributions, and the bayesian restoration of images","volume":"6","author":"Geman","year":"1984","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026032615264574400_ref025","first-page":"443","article-title":"Fixing max-product: Convergent message passing algorithms for MAP LP-relaxations","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Globerson","year":"2007"},{"issue":"6","key":"2026032615264574400_ref026","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1016\/j.media.2008.03.006","article-title":"Dense image registration through MRFs and efficient linear programming","volume":"12","author":"Glocker","year":"2008","journal-title":"Medical Image Analysis"},{"key":"2026032615264574400_ref027","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2008.4587562","article-title":"Optical flow estimation with uncertainties through dynamic MRFs","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Glocker","year":"2008"},{"key":"2026032615264574400_ref028","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1146\/annurev-bioeng-071910-124649","article-title":"Deformable medical image registration: setting the state of the art with discrete methods","volume":"13","author":"Glocker","year":"2011","journal-title":"Annual Reviews Biomedical Engineering"},{"key":"2026032615264574400_ref029","first-page":"652","article-title":"A constant factor approximation algorithm for a class of classification problems","volume-title":"Proceedings of the Annual ACM Symposium on Theory of Computing","author":"Gupta","year":"2000"},{"key":"2026032615264574400_ref030","first-page":"97","article-title":"Joint 3D scene reconstruction and class segmentation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Hane","year":"2013"},{"issue":"12","key":"2026032615264574400_ref031","doi-asserted-by":"crossref","first-page":"6294","DOI":"10.1109\/TIT.2010.2079014","article-title":"Norm-product belief propagation: Primal-dual message-passing for approximate inference","volume":"56","author":"Hazan","year":"2010","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026032615264574400_ref032","first-page":"1754","article-title":"Discrete tracking of parametrized curves","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Heibel","year":"2009"},{"key":"2026032615264574400_ref033","volume-title":"Approximation Algorithms for NP-hard Problems","author":"Hochbaum","year":"1997"},{"issue":"10","key":"2026032615264574400_ref034","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1109\/TPAMI.2003.1233908","article-title":"Exact optimization for Markov random fields with convex priors","volume":"25","author":"Ishikawa","year":"2003","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026032615264574400_ref035","first-page":"1313","article-title":"Reflection methods for user-friendly submodular optimization","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Jegelka","year":"2013"},{"key":"2026032615264574400_ref036","first-page":"503","article-title":"Fast and smooth: Accelerated dual decomposition for MAP inference","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Jojic","year":"2010"},{"issue":"16-17","key":"2026032615264574400_ref037","doi-asserted-by":"crossref","first-page":"2419","DOI":"10.1016\/j.dam.2012.06.009","article-title":"Generalized roof duality","volume":"160","author":"Kahl","year":"2012","journal-title":"Discrete Applied Mathematics"},{"issue":"2","key":"2026032615264574400_ref038","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/s11263-015-0809-x","article-title":"A comparative study of mo dern inference techniques for structured discrete energy minimization problems","volume":"115","author":"Kappes","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"2026032615264574400_ref039","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.cviu.2015.10.016","article-title":"Lazy generic cuts","volume":"143","author":"Khandelwal","year":"2016","journal-title":"Computer Vision and Image Understanding"},{"key":"2026032615264574400_ref040","first-page":"14","article-title":"Approximation algorithms for classification problems with pairwise relationships: Metric labeling and Markov random fields","volume-title":"Proceedings of the Annual ACM Symposium on Theory of Computing","author":"Kleinberg","year":"1999"},{"issue":"9","key":"2026032615264574400_ref041","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1109\/TPAMI.2008.217","article-title":"P3 and beyond: Move making algorithms for solving higher order functions","volume":"31","author":"Kohli","year":"2009","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intel ligence"},{"issue":"3","key":"2026032615264574400_ref042","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1007\/s11263-008-0202-0","article-title":"Robust higher order potentials for enforcing label consistency","volume":"82","author":"Kohli","year":"2009","journal-title":"International Journal of Computer Vision"},{"issue":"10","key":"2026032615264574400_ref043","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1109\/TPAMI.2006.200","article-title":"Convergent tree-reweighted message passing for energy minimization","volume":"28","author":"Kolmogorov","year":"2006","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intel ligence"},{"key":"2026032615264574400_ref044","first-page":"1144","article-title":"Generalized roof duality and bisubmodular functions","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Kolmogorov"},{"issue":"1","key":"2026032615264574400_ref045","first-page":"14","article-title":"Minimizing a sum of submodular functions","volume":"112","author":"Kolmogorov","year":"2012","journal-title":"Discrete Applied Mathematics"},{"issue":"4","key":"2026032615264574400_ref046","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1016\/j.disopt.2009.04.006","article-title":"New algorithms for convex cost tension problem with application to computer vision","volume":"6","author":"Kolmogorov","year":"2009","journal-title":"Discrete Optimization"},{"issue":"2","key":"2026032615264574400_ref047","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1109\/TPAMI.2004.1262177","article-title":"What energy functions can be minimized via graph cuts?","volume":"26","author":"Kolmogorov","year":"2004","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intel ligence"},{"key":"2026032615264574400_ref048","first-page":"520","article-title":"Towards more efficient and effective lp-based algorithms for MRF optimization","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Komodakis","year":"2010"},{"key":"2026032615264574400_ref049","first-page":"73","article-title":"Learning to cluster using high order graphical models with latent variables","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Komodakis","year":"2011"},{"key":"2026032615264574400_ref050","first-page":"806","article-title":"Beyond loose LP-relaxations: Optimizing MRFs by repairing cycles","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Komodakis","year":"2008"},{"key":"2026032615264574400_ref051","first-page":"2985","article-title":"Beyond pairwise energies: Efficient optimization for higher-order MRFs","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Komodakis","year":"2009"},{"key":"2026032615264574400_ref052","first-page":"361","article-title":"MRF-based blind image deconvolution","volume-title":"Proceedings of the Asian Conference on Computer Vision","author":"Komodakis","year":"2012"},{"issue":"11","key":"2026032615264574400_ref053","doi-asserted-by":"crossref","first-page":"2649","DOI":"10.1109\/TIP.2007.906269","article-title":"Image completion using efficient belief propagation via priority scheduling and dynamic pruning","volume":"16","author":"Komodakis","year":"2007","journal-title":"IEEE Transactions on Image Processing"},{"issue":"8","key":"2026032615264574400_ref054","doi-asserted-by":"crossref","first-page":"1436","DOI":"10.1109\/TPAMI.2007.1061","article-title":"Approximate labeling via graph-cuts based on linear programming","volume":"29","author":"Komodakis","year":"2007","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"2026032615264574400_ref055","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.cviu.2008.06.007","article-title":"Performance vs computational efficiency for optimizing single and dynamic MRFs: Setting the state of the art with primal-dual strategies","volume":"112","author":"Komodakis","year":"2008","journal-title":"Computer Vision and Image Understanding"},{"issue":"3","key":"2026032615264574400_ref056","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1109\/TPAMI.2010.108","article-title":"MRF energy minimization and beyond via dual decomposition","volume":"33","author":"Komodakis","year":"2011","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"2026032615264574400_ref057","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1109\/TPAMI.2014.2368990","article-title":"A framework for efficient structured max-margin learning of high-order MRF models","volume":"37","author":"Komodakis","year":"2015","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2026032615264574400_ref058","first-page":"109","article-title":"Rounding-based moves for metric labeling","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Kumar","year":"2014"},{"key":"2026032615264574400_ref059","first-page":"313","article-title":"MAP estimation of semi-metric MRFs via hierarchical graph cuts","volume-title":"Proceedings of the Conference on Uncertainty in Artificial Intelligence","author":"Kumar","year":"2009"},{"key":"2026032615264574400_ref060","first-page":"3217","article-title":"Efficiently selecting regions for scene understanding","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Kumar","year":"2010"},{"key":"2026032615264574400_ref061","first-page":"889","article-title":"Improved moves for truncated convex models","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Kumar","year":"2008"},{"key":"2026032615264574400_ref062","first-page":"1041","article-title":"An analysis of convex relaxations for MAP estimation","volume-title":"Proceedings of the Annual Conference on Neural Information Processing Systems","author":"Kumar","year":"2007"},{"issue":"1","key":"2026032615264574400_ref063","first-page":"14","article-title":"Inference methods for CRFs with co-occurence statistics","volume":"62","author":"Ladicky","year":"2013","journal-title":"International Journal of Computer Vision"},{"key":"2026032615264574400_ref064","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/s101070050090","article-title":"Ergodic primal convergence in dual subgradient schemes for convex programming","volume":"86","author":"Larsson","year":"1999","journal-title":"Mathematical Programming"},{"key":"2026032615264574400_ref065","first-page":"11","article-title":"SDP gaps and UGC hardness for multiway cut, 0-extension and metric labeling","volume-title":"Proceedings of the Annual ACM Symposium on Theory of Computing","author":"Manokaran","year":"2008"},{"key":"2026032615264574400_ref066","first-page":"467","article-title":"Loopy belief propagation for approximate inference: An empirical study","volume-title":"Proceedings of the Conference on Uncertainty in Artificial Intelligence","author":"Murphy","year":"1999"},{"key":"2026032615264574400_ref067","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1137\/S1052623499362111","article-title":"Incremental subgradient methods for non-differentiable optimization","volume":"12","author":"Nedic","year":"2001","journal-title":"SIAM Journal on Optimization"},{"key":"2026032615264574400_ref068","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1137\/070708111","article-title":"Approximate primal solutions and rate analysis for dual subgradient methods","volume":"19","author":"Nedic","year":"2009","journal-title":"SIAM Journal on Optimization"},{"key":"2026032615264574400_ref069","first-page":"1889","article-title":"Submodular decomposition framework for inference in associative markov networks with global constraints","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Osokin","year":"2011"},{"key":"2026032615264574400_ref070","volume-title":"Combinatorial Optimization: Algorithms and Complexity","author":"Papadimitriou","year":"1982"},{"key":"2026032615264574400_ref071","first-page":"18","article-title":"Discrete visual perception","volume-title":"Proceedings of the International Conference on Pattern Recognition","author":"Paragios","year":"2014"},{"key":"2026032615264574400_ref072","volume-title":"Probabilistic Reasoning in Intel ligent Systems: Networks of Plausible Inference","author":"Pearl","year":"1998"},{"key":"2026032615264574400_ref073","first-page":"792","article-title":"A convex formulation of continuous multi-label problems","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Pock","year":"2008"},{"key":"2026032615264574400_ref074","first-page":"810","article-title":"A convex relaxation approach for computing minimal partitions","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Pock","year":"2009"},{"key":"2026032615264574400_ref075","doi-asserted-by":"crossref","DOI":"10.1017\/S0305004100027419","article-title":"Some generalized order-disorder transformations","volume-title":"Cambridge Philosophical Society","author":"Potts","year":"1952"},{"key":"2026032615264574400_ref076","first-page":"1817","article-title":"A study of Nesterov\u2019s scheme for Lagrangian decomposition and MAP labeling","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Savchynskyy","year":"2011"},{"key":"2026032615264574400_ref077","first-page":"746","article-title":"Efficient MRF energy minimization via adaptive diminishing smoothing","volume-title":"Conference on Uncertainty in Artificial Intelligence","author":"Savchynskyy","year":"2012"},{"key":"2026032615264574400_ref078","first-page":"113","article-title":"Sintaksicheskiy analiz dvumernykh zritelnikh signalov vusloviyakh pomekh (syntactic analysis of two-dimensional visual signals in noisy conditions)","volume":"4","author":"Schlesinger","year":"1976","journal-title":"Kibernetika"},{"key":"2026032615264574400_ref079","first-page":"717","article-title":"Polynomial-time exact inference in NP-hard binary MRFs via reweighted perfect matching","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Schraudolph","year":"2010"},{"key":"2026032615264574400_ref080","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/0167-6377(96)00019-3","article-title":"Recovery of primal solutions when using subgradient optimization methods to solve lagrangian duals of linear programs","volume":"19","author":"Sherali","year":"1996","journal-title":"Operations Research Letters"},{"key":"2026032615264574400_ref081","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-82118-9","volume-title":"Minimization methods for nondifferentiable functions","author":"Shor","year":"1985"},{"key":"2026032615264574400_ref082","first-page":"770","article-title":"Tightening LP relaxations for MAP using message passing","volume-title":"Conference on Uncertainty in Artificial Intelligence","author":"Sontag","year":"2008"},{"key":"2026032615264574400_ref083","first-page":"1621","article-title":"Learning to detect ground control points for improving the accuracy of stereo matching","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Spyropoulos","year":"2014"},{"issue":"12","key":"2026032615264574400_ref084","doi-asserted-by":"crossref","first-page":"1721","DOI":"10.1016\/j.cviu.2011.06.012","article-title":"Parallel and distributed vision algorithms using dual decomposition","volume":"115","author":"Strandmark","year":"2011","journal-title":"Computer Vision and Image Understanding"},{"issue":"6","key":"2026032615264574400_ref085","doi-asserted-by":"crossref","first-page":"1068","DOI":"10.1109\/TPAMI.2007.70844","article-title":"A comparative study of energy minimization methods for Markov random fields with smoothness-based priors","volume":"30","author":"Szeliski","year":"2008","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"2026032615264574400_ref086","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1109\/TPAMI.2012.105","article-title":"A dual decomposition approach to feature correspondence","volume":"35","author":"Torresani","year":"2013","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intel ligence"},{"issue":"2","key":"2026032615264574400_ref087","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1007\/s11263-011-0512-5","article-title":"Motion coherent tracking using multi-label MRF optimization","volume":"100","author":"Tsai","year":"2012","journal-title":"International Journal of Computer Vision"},{"key":"2026032615264574400_ref088","first-page":"61","article-title":"Simultaneous registration and change detection in multitemporal, very high resolution remote sensing data","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Vakalopoulou","year":"2015"},{"key":"2026032615264574400_ref089","volume-title":"Approximation Algorithms","author":"Vazirani","year":"2001"},{"key":"2026032615264574400_ref090","volume-title":"Efficient Graph-based Energy Minimization Methods in Computer Vision","author":"Veksler","year":"1999"},{"key":"2026032615264574400_ref091","first-page":"1","article-title":"Graph cut based optimization for MRFs with truncated convex priors","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Veksler","year":"2007"},{"key":"2026032615264574400_ref092","first-page":"755","article-title":"Joint optimization of segmentation and appearance models","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Vicente","year":"2009"},{"key":"2026032615264574400_ref093","first-page":"65","article-title":"Map estimation via agreement on trees: message-passing and linear programming","volume":"30","author":"Wainwright","year":"2005","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026032615264574400_ref094","first-page":"1295","article-title":"Segmentation, ordering and multi-object tracking using graphical models","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Wang","year":"2009"},{"key":"2026032615264574400_ref095","first-page":"801","article-title":"3D knowledgebased segmentation using pose-invariant higher-order graphs","volume-title":"Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention","author":"Wang","year":"2010"},{"issue":"11","key":"2026032615264574400_ref096","doi-asserted-by":"crossref","first-page":"1610","DOI":"10.1016\/j.cviu.2013.07.004","article-title":"Markov random field modeling, inference & learning in computer vision & image understanding: A survey","volume":"117","author":"Wang","year":"2013","journal-title":"Computer Vision and Image Understanding"},{"issue":"2","key":"2026032615264574400_ref097","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1109\/18.910585","article-title":"On the optimality of solutions of the max-product belief propagation algorithm in arbitrary graphs","volume":"47","author":"Weiss","year":"2001","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026032615264574400_ref098","first-page":"102","article-title":"A linear programming approach to max-sum problem: A review","volume":"22","author":"Werner","year":"2007","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intel ligence"},{"key":"2026032615264574400_ref099","first-page":"2319","article-title":"A global perspective on MAP inference for low-level vision","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Woodford","year":"2009"},{"key":"2026032615264574400_ref100","first-page":"194","article-title":"Pose invariant deformable shape priors using L1 higher order sparse graphs","volume-title":"Proceedings of the International Symposium on Visual Computing","author":"Xiang","year":"2013"},{"key":"2026032615264574400_ref101","first-page":"153","article-title":"Linear Programming Relaxations and Belief Propagation \u2013 An Empirical Study","volume":"7","author":"Yanover","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"2026032615264574400_ref102","first-page":"770","article-title":"Tightening MRF relaxations with planar subproblems","volume-title":"Conference on Uncertainty in Artificial Intelligence","author":"Yarkony","year":"2011"},{"key":"2026032615264574400_ref103","first-page":"1225","article-title":"Intrinsic dense 3D surface tracking","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zeng","year":"2011"},{"key":"2026032615264574400_ref104","first-page":"142","article-title":"A map-estimation framework for blind deblurring using high-level edge priors","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Zhou","year":"2014"}],"container-title":["Foundations and Trends\u00ae in Computer Graphics and Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/ftcgv\/article-pdf\/10\/1\/1\/11023942\/0600000066en.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ftcgv\/article-pdf\/10\/1\/1\/11023942\/0600000066en.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T14:09:12Z","timestamp":1777471752000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ftcgv\/article\/10\/1\/1\/1326445\/Hyper-Graphs-Inference-through-Convex-Relaxations"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,5,31]]},"references-count":104,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,5,31]]}},"URL":"https:\/\/doi.org\/10.1561\/0600000066","relation":{},"ISSN":["1572-2740","1572-2759"],"issn-type":[{"value":"1572-2740","type":"print"},{"value":"1572-2759","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,5,31]]}}}