{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/joint-graph-decomposition-and-node-labeling","title":"Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications","arxiv_id":"1611.04399","date":"2016-11-14","proceeding":null,"authors":["Evgeny Levinkov","Jonas Uhrig","Siyu Tang","Mohamed Omran","Eldar Insafutdinov","Alexander Kirillov","Carsten Rother","Thomas Brox","Bernt Schiele","Bjoern Andres"],"abstract":"We state a combinatorial optimization problem whose feasible solutions define\nboth a decomposition and a node labeling of a given graph. This problem offers\na common mathematical abstraction of seemingly unrelated computer vision tasks,\nincluding instance-separating semantic segmentation, articulated human body\npose estimation and multiple object tracking. Conceptually, the problem we\nstate generalizes the unconstrained integer quadratic program and the minimum\ncost lifted multicut problem, both of which are NP-hard. In order to find\nfeasible solutions efficiently, we define two local search algorithms that\nconverge monotonously to a local optimum, offering a feasible solution at any\ntime. To demonstrate their effectiveness in tackling computer vision tasks, we\napply these algorithms to instances of the problem that we construct from\npublished data, using published algorithms. We report state-of-the-art\napplication-specific accuracy for the three above-mentioned applications.","url_abs":"http://arxiv.org/abs/1611.04399v2","url_pdf":"http://arxiv.org/pdf/1611.04399v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"joint-graph-decomposition-and-node-labeling","repo_url":"https://github.com/bjoern-andres/graph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"combinatorial-optimization","task_name":"Combinatorial Optimization"},{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.04399","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}