A Tensor-Based Algorithm for High-Order Graph Matching
Abstract
This paper addresses the problem of establishing correspondences between two sets of visual features using higher-order constraints instead of the unary or pairwise ones used in classical methods. Concretely, the corresponding hypergraph matching problem is formulated as the maximization of a multilinear objective function over all permutations of the features. This function is defined by a tensor representing the affinity between feature tuples. It is maximized using a generalization of spectral techniques where a relaxed problem is first solved by a multi-dimensional power method, and the solution is then projected onto the closest assignment matrix. The proposed approach has been implemented, and it is compared to state-of-the-art algorithms on both synthetic and real data.
Cite
Text
Duchenne et al. "A Tensor-Based Algorithm for High-Order Graph Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206619Markdown
[Duchenne et al. "A Tensor-Based Algorithm for High-Order Graph Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/duchenne2009cvpr-tensor/) doi:10.1109/CVPR.2009.5206619BibTeX
@inproceedings{duchenne2009cvpr-tensor,
title = {{A Tensor-Based Algorithm for High-Order Graph Matching}},
author = {Duchenne, Olivier and Bach, Francis R. and Kweon, In-So and Ponce, Jean},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2009},
pages = {1980-1987},
doi = {10.1109/CVPR.2009.5206619},
url = {https://mlanthology.org/cvpr/2009/duchenne2009cvpr-tensor/}
}