{"type":"ScholarlyArticle","title":"Dynamic Programming Bipartite Belief Propagation For Hyper Graph Matching","authors":[{"name":"Zhen Zhang","slug":"zhen-zhang","given":"Zhen","family":"Zhang","affiliation":"School of Computer Science & Engineering , Northwestern Polytechnical University , Xi'an , China"},{"name":"Julian McAuley","slug":"julian-mcauley","given":"Julian","family":"McAuley","affiliation":"Computer Science and Engineering Department , University of California , San Diego , USA"},{"name":"Yong Li","slug":"yong-li","given":"Yong","family":"Li","affiliation":"School of Computer Science & Engineering , Northwestern Polytechnical University , Xi'an , China"},{"name":"Wei Wei","slug":"wei-wei","given":"Wei","family":"Wei","affiliation":"School of Computer Science & Engineering , Northwestern Polytechnical University , Xi'an , China"},{"name":"Yanning Zhang","slug":"yanning-zhang","given":"Yanning","family":"Zhang","affiliation":"School of Computer Science & Engineering , Northwestern Polytechnical University , Xi'an , China"},{"name":"Qinfeng Shi","slug":"qinfeng-shi","given":"Qinfeng","family":"Shi","affiliation":"School of Computer Science , The University of Adelaide , Australia"}],"abstract":"Hyper graph matching problems have drawn attention recently due to their ability to embed higher order relations between nodes.  In this paper, we formulate hyper graph matching problems as constrained MAP inference problems in graphical models. Whereas previous discrete approaches introduce several global correspondence vectors, we introduce only one global correspondence vector, but several local correspondence vectors. This allows us to decompose the problem into a (linear) bipartite matching problem and several belief propagation sub-problems. Bipartite matching can be solved by traditional approaches, while the belief propagation sub-problem is further decomposed as two sub-problems with optimal substructure. Then a newly proposed dynamic programming procedure is used to solve the belief propagation sub-problem. Experiments show that the proposed methods outperform state-of-the-art techniques for hyper graph matching.","doi":"10.24963/ijcai.2017/650","url":"https://ijcai.org/proceedings/2017/650","pdf":"https://ijcai.org/proceedings/2017/0650.pdf","markdown":"https://ijcai.org/proceedings/2017/650.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/650","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Uncertainty in AI","track":"Main track","number":650,"pages":{"first":4662,"last":4668},"keywords":["Robotics and Vision: Localization, Mapping, State Estimation","Uncertainty in AI: Graphical Models","Uncertainty in AI: Approximate Probabilistic Inference"],"videos":[],"references":[{"position":1,"raw":"[Ahn et al., 2015] Sung-Soo Ahn, Sejun Park, Michael Chertkov, and Jinwoo Shin. Minimum weight perfect matching via blossom belief propagation. In NIPS, 2015.","title":"Minimum weight perfect matching via blossom belief propagation","authors":"Sung-Soo Ahn, Sejun Park, Michael Chertkov, Jinwoo Shin","year":"2015","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cho et al., 2014] Minsu Cho, Jian Sun, Olivier Duchenne, and Jean Ponce. Finding matches in a haystack: A max- pooling strategy for graph matching in the presence of out- liers. In CVPR, 2014.","title":"Finding matches in a haystack: A maxpooling strategy for graph matching in the presence of outliers","authors":"Minsu Cho, Jian Sun, Olivier Duchenne, Jean Ponce","year":"2014","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Duchenne et al., 2009] Olivier Duchenne, F Bach, In-So Kweon, and J Ponce. A tensor-based algorithm for high- order graph matching. In CVPR, 2009.","title":"A tensor-based algorithm for highorder graph matching","authors":"Olivier Duchenne, In-So Bach, Kweon, Ponce","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Everingham et al., 2009] Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisser- man. The PASCAL visual object classes challenge. In PASCAL Challenge Workshop, 2009.","title":"The PASCAL visual object classes challenge","authors":"Mark Everingham, Luc Van Gool, K I Christopher, John Williams, Andrew Winn, Zisserman","year":"2009","venue":"PASCAL Challenge Workshop","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Lee et al., 2011] Jungmin Lee, Minsu Cho, and Kyoung Mu Lee. Hyper-graph matching via reweighted random walks. In CVPR, 2011.","title":"Hyper-graph matching via reweighted random walks","authors":"Jungmin Lee, Minsu Cho, Kyoung Mu, Lee","year":"2011","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Leordeanu and Hebert, 2005] Marius Leordeanu and Mar- tial Hebert. A spectral technique for correspondence prob- lems using pairwise constraints. In Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on, vol- ume 2, pages 1482-1489. IEEE, 2005.","title":"Marius Leordeanu and Martial Hebert. A spectral technique for correspondence problems using pairwise constraints","authors":"Hebert Leordeanu","year":"2005","venue":"Tenth IEEE International Conference on","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Leordeanu et al., 2009] Marius Leordeanu, Martial Hebert, and Rahul Sukthankar. An integer projected fixed point method for graph matching and MAP inference. In NIPS, 2009.","title":"An integer projected fixed point method for graph matching and MAP inference","authors":"Marius Leordeanu, Martial Hebert, Rahul Sukthankar","year":"2009","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Li et al., 2010] Hongsheng Li, Edward Kim, Xiaolei Huang, and Lei He. Object matching with a locally affine-invariant constraint. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages 1641-1648. IEEE, 2010.","title":"Object matching with a locally affine-invariant constraint","authors":"Hongsheng Li, Edward Kim, Xiaolei Huang, Lei He","year":"2010","venue":"Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Munkres, 1957] James Munkres. Algorithms for the assign- ment and transportation problems. Journal of the society for industrial and applied mathematics, 5(1):32-38, 1957.","title":"Algorithms for the assignment and transportation problems","authors":"James Munkres","year":"1957","venue":"Journal of the society for industrial and applied mathematics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Nguyen et al., 2015] Quynh Nguyen, Antoine Gautier, and Matthias Hein. A flexible tensor block coordinate ascent scheme for hypergraph matching. In CVPR, 2015.","title":"A flexible tensor block coordinate ascent scheme for hypergraph matching","authors":"Quynh Nguyen, Antoine Gautier, Matthias Hein","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Potetz and Lee, 2008] Brian Potetz and Tai Sing Lee. Effi- cient belief propagation for higher-order cliques using lin- ear constraint nodes. Computer Vision and Image Under- standing, 112(1):39-54, 2008.","title":"Efficient belief propagation for higher-order cliques using linear constraint nodes","authors":"Lee ; Potetz, Brian Potetz, Tai Sing, Lee","year":"2008","venue":"Computer Vision and Image Understanding","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Rother et al., 2009] Carsten Rother, Pushmeet Kohli, Wei Feng, and Jiaya Jia. Minimizing sparse higher order en- ergy functions of discrete variables. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Con- ference on, pages 1382-1389. IEEE, 2009.","title":"Minimizing sparse higher order energy functions of discrete variables","authors":"Carsten Rother, Pushmeet Kohli, Wei Feng, Jiaya Jia","year":"2009","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Torresani et al., 2008] Lorenzo Torresani, Vladimir Kol- mogorov, and Carsten Rother. Feature correspondence via graph matching: Models and global optimization. In ECCV, 2008.","title":"Feature correspondence via graph matching: Models and global optimization","authors":"Lorenzo Torresani, Vladimir Kolmogorov, Carsten Rother","year":"2008","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Werner, 2007] Tomas Werner. A linear programming ap- proach to max-sum problem: A review. IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 29(7):1165-1179, 2007.","title":"A linear programming approach to max-sum problem: A review","authors":"Tomas Werner","year":"2007","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Yan et al., 2015] Junchi Yan, Chao Zhang, Hongyuan Zha, Wei Liu, Xiaokang Yang, and Stephen M Chu. Discrete hyper-graph matching. In CVPR, 2015.","title":"Discrete hyper-graph matching","authors":"Yan","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Zass and Shashua, 2008] Ron Zass and Amnon Shashua. Probabilistic graph and hypergraph matching. In CVPR, 2008.","title":"Probabilistic graph and hypergraph matching","authors":"Ron Zass, Amnon Shashua","year":"2008","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Zhang et al., 2016] Zhen Zhang, Qinfeng Shi, Julian McAuley, Wei Wei, Yanning Zhang, and Anton van den Hengel. Pairwise matching through max-weight bipartite belief propagation. In CVPR, 2016.","title":"Pairwise matching through max-weight bipartite belief propagation","authors":"Zhen Zhang, Qinfeng Shi, Julian Mcauley, Wei Wei, Yanning Zhang, Anton Van Den, Hengel","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Zhou and De la Torre, 2012] Feng Zhou and Fernando De la Torre. Factorized graph matching. In CVPR, 2012.","title":"Feng Zhou and Fernando De la Torre. Factorized graph matching","authors":"De Zhou, Torre La","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}