Factorized Graph Matching

481 citations recorded by the source corpus.

How researchers see this paper

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

SOSNet: Second Order Similarity Regularization for Local Descriptor Learning (2019, methodology): “Second Order Similarity (SOS) has been used for graph matching and clustering tasks [10, 11, 43], due to the fact that it can capture more structural information such as shape and scale, while at the same time being robust to deforma-”
Matching Guided Distillation (2020, background): “Linear Assignment (LA) is the most classical correspondence problem that can be efficiently solved with Hungarian algorithm [20], unlike the NP-hard quadratic assignment problem [43].”
A comprehensive survey on point cloud registration (2021, background): “FGM [117] factorizes the large pairwise afﬁnity matrix into some smaller matrices.”
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.”