An Integer Projected Fixed Point Method for Graph Matching and MAP Inference

By Marius Leordeanu, Martial Hebert, Rahul Sukthankar. Neural Information Processing Systems, 2009

357 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/692a262fab75e1cdefb8cffa5ba7be7cf988b939

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “Leordeanu et al. (2009) proposed an efficient algorithm that optimizes in the (quasi) discrete domain via solving a sequence of linear assignment problems.”
Factorized Graph Matching (2016, methodology): “[39] proposed an integer projection algorithm to optimize the objective function in an integer domain.”
Clique-graph matching by preserving global & local structure (2015, unknown): “Different from previous graph matching methods which consider each node as the basic unit, we propose to regard each clique as the basic unit for matching, which consists of several neighbor nodes in the feature space and can implicitly convey arbitrary order attributes with the specific structure.”
Reweighted Random Walks for Graph Matching (2010, methodology): “They also recently proposed an iterative matching method (IPFP) [8] with climbing and convergence properties which optimizes the IQP in the discrete domain.”
Representing Videos Using Mid-level Discriminative Patches (2013, methodology): “The SVM parameters for classification are selected through cross validation.”
Features in Concert: Discriminative Feature Selection meets Unsupervised Clustering (2014, methodology): “An efficient clustering method that is one to two orders of magnitude faster in practice than interior point convex optimization, based on recent work on the IPFP algorithm [28] and the Frank-Wolfe method [14].”
Solving the multi-way matching problem by permutation synchronization (2013, background): “Recent solutions often leverage supervision to make the problem tractable [24, 25].”