Name
Abstract | ||
|---|---|---|
We describe a generative model of the relationship between two images. The model is defined as a factored three-way Boltzmann machine, in which hidden variables collaborate to define the joint correlation matrix for image pairs. Modeling the joint distribution over pairs makes it possible to efficiently match images that are the same according to a learned measure of similarity. We apply the model to several face matching tasks, and show that it learns to represent the input images using task-specific basis functions. Matching performance is superior to previous similar generative models, including recent conditional models of transformations. We also show that the model can be used as a plug-in matching score to perform invariant classification. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/CVPR.2011.5995541 | Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
Boltzmann machines,correlation theory,face recognition,image matching,face matching,hidden variable collaboration,image pair,images match,joint correlation matrix,joint density modeling,matching performance,plug-in matching,similar generative model,task-specific basis function,three-way Boltzmann machine | Facial recognition system,Computer vision,Boltzmann machine,Joint probability distribution,Pattern recognition,Computer science,Basis function,Artificial intelligence,Invariant (mathematics),Covariance matrix,Discriminative model,Generative model | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
978-1-4577-0394-2 | 17 | 1.53 |
References | Authors | |
8 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Joshua Susskind | 1 | 194 | 9.68 |
| Memisevic, R. | 2 | 17 | 1.53 |
| geoffrey e hinton | 3 | 40435 | 4751.69 |
| Marc Pollefeys | 4 | 7671 | 475.90 |