Reweighted Random Walks for Graph Matching

By Minsu Cho, Jungmin Lee, Kyoung Mu Lee. European Conference on Computer Vision, 2010

540 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/2edace819fc4b52018678e44b610144f7dddb789

How researchers see this paper

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

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

Factorized Graph Matching (2016, methodology): “[43] introduced a random-walk algorithm to approximate GM problem.”
A review of multimodal image matching: Methods and applications (2021, methodology): “Many others, such as random walk method [264] and Monte Carlo method [265,266], are also investigated for the GM problem.”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “The RRWM remains competitive with high accuracy and low runtime.”
Grounding Image Matching in 3D with MASt3R (2024, methodology): “Contrary to the traditional bipartite graph matching formulation [18], where the complete graph is used for the matching, we wish to decrease the computational complexity by calculating only a smaller portion of it.”
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency (2021, methodology): “Thus, geometric consistency, such as length constraint under rigid transformation, becomes important and is commonly utilized by traditional outlier rejection algorithms and analyzed through spectral techniques [36, 20], voting schemes [26, 69, 57], maximum clique [50, 12, 59], random walk [14], bel”
Finding Matches in a Haystack: A Max-Pooling Strategy for Graph Matching in the Presence of Outliers (2014, methodology): “MPM can be compared with other graph matching algorithms, which adopt a similar iterative optimization strategy [6, 9, 14, 18].”
Clique-graph matching by preserving global & local structure (2015, background): “Given two sets of feature points lying in different subspaces, each set can be considered as one graph, which consists of two important components, nodes and edges, respectively representing feature points and the relations between pariwise feature points.”
Dynamic Label Graph Matching for Unsupervised Video Re-identification (2017, background): “The relationships between nodes and edges are usually represented by assignment cost matrix [13, 4] or affinity matrix [2, 28].”
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-”