{"page":"16","day":"29","publication":"arXiv","author":[{"first_name":"Vladimir","last_name":"Kolmogorov","id":"3D50B0BA-F248-11E8-B48F-1D18A9856A87","full_name":"Kolmogorov, Vladimir"},{"first_name":"Thomas","last_name":"Schoenemann","full_name":"Schoenemann, Thomas"}],"type":"preprint","date_updated":"2021-01-12T07:00:45Z","external_id":{"arxiv":["1205.6352"]},"article_processing_charge":"No","month":"05","citation":{"mla":"Kolmogorov, Vladimir, and Thomas Schoenemann. “Generalized Sequential Tree-Reweighted Message Passing.” <i>ArXiv</i>, ArXiv, 2012.","ieee":"V. Kolmogorov and T. Schoenemann, “Generalized sequential tree-reweighted message passing,” <i>arXiv</i>. ArXiv, 2012.","apa":"Kolmogorov, V., &#38; Schoenemann, T. (2012). Generalized sequential tree-reweighted message passing. <i>arXiv</i>. ArXiv.","ista":"Kolmogorov V, Schoenemann T. 2012. Generalized sequential tree-reweighted message passing. arXiv, .","chicago":"Kolmogorov, Vladimir, and Thomas Schoenemann. “Generalized Sequential Tree-Reweighted Message Passing.” <i>ArXiv</i>. ArXiv, 2012.","ama":"Kolmogorov V, Schoenemann T. Generalized sequential tree-reweighted message passing. <i>arXiv</i>. 2012.","short":"V. Kolmogorov, T. Schoenemann, ArXiv (2012)."},"date_published":"2012-05-29T00:00:00Z","publication_status":"published","main_file_link":[{"url":"http://arxiv.org/abs/1205.6352","open_access":"1"}],"abstract":[{"lang":"eng","text":"     This paper addresses the problem of approximate MAP-MRF inference in general graphical models. Following [36], we consider a family of linear programming relaxations of the problem where each relaxation is specified by a set of nested pairs of factors for which the marginalization constraint needs to be enforced. We develop a generalization of the TRW-S algorithm [9] for this problem, where we use a decomposition into junction chains, monotonic w.r.t. some ordering on the nodes. This generalizes the monotonic chains in [9] in a natural way. We also show how to deal with nested factors in an efficient way. Experiments show an improvement over min-sum diffusion, MPLP and subgradient ascent algorithms on a number of computer vision and natural language processing problems. "}],"department":[{"_id":"VlKo"}],"language":[{"iso":"eng"}],"_id":"2928","date_created":"2018-12-11T12:00:23Z","publist_id":"3809","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa":1,"oa_version":"Preprint","publisher":"ArXiv","year":"2012","status":"public","title":"Generalized sequential tree-reweighted message passing"}