Modeling the joint density of two images under a variety of transformations

  title={Modeling the joint density of two images under a variety of transformations},
  author={Joshua M. Susskind and Geoffrey E. Hinton and Roland Memisevic and Marc Pollefeys},
  journal={CVPR 2011},
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… CONTINUE READING
Highly Cited
This paper has 56 citations. REVIEW CITATIONS
42 Citations
28 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 42 extracted citations

57 Citations

Citations per Year
Semantic Scholar estimates that this publication has 57 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 28 references

Making Boltzmann machines sharper by using dissatisfied covariance constraints

  • M. Ranzato, G. Hinton
  • In Proceedings of IEEE Conference on Computer…
  • 2010
Highly Influential
4 Excerpts

The Toronto face database

  • J. M. Susskind, A. K. Anderson, G. E. Hinton
  • Technical report, Toronto, ON, Canada,
  • 2010
Highly Influential
5 Excerpts

Similar Papers

Loading similar papers…