A tensor-based algorithm for high-order graph matching

By Olivier Duchenne, Francis R. Bach, In-So Kweon, Jean Ponce. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009

483 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/239a470bf02fbed511b8e83de901280878cb8902

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

Citations in the corpus

Deformable Medical Image Registration: A Survey (2013, methodology): “Duchenne et al. [290] generalized the spectral matching method [287] to higher order constraints.”
Fast Exact Hyper-graph Matching with Dynamic Programming for Spatio-temporal Data (2014, unknown): “[31] made an improvement on the solution to the integer quadratic programming problem in [14] by introducing a semi-supervised learning approach.”
Deep Metric Learning with Angular Loss (2017, methodology): “Our idea is analogous to the usage of high-order information for augmenting pair-wise constraints in the domain of graph matching [9] and Markov random ﬁelds [10].”
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, background): “, [105], [106] which consider ternary relationships) are emerging.”
Factorized Graph Matching (2016, methodology): “The CMU house image sequence5 was commonly used to test the performance of graph matching algorithms [40], [44], [47], [49].”
Reweighted Random Walks for Graph Matching (2010, methodology): “First, it establishes a novel random walk view for graph matching and provides a basis for random walk interpretations of recent spectral matching [3,4,7] and other iterative algorithms [13,6].”
A comprehensive survey on point cloud registration (2021, methodology): “High-order GM methods involve more than two points, such as similarity of triangle pairs [23].”
TRAR: Routing the Attention Spans in Transformer for Visual Question Answering (2021, methodology): “Our definition is similar to it, except that we use the concept of order neighborhood from graph topology [12] to denote different degrees of attention spans, e.”
Image Matching from Handcrafted to Deep Features: A Survey (2020, methodology): “2010), TM (Duchenne et al. 2011), GNCCP (Liu and Qiao 2014), and FGM (Zhou and De la Torre 2015) on several extensively used and publicly available datasets.”
An introduction to domain adaptation and transfer learning (2018, methodology): “These can be found using tensor-based algorithms [50,60].”