Learning the “ Epitome ” of an Image

@inproceedings{Frey2002LearningT,
  title={Learning the “ Epitome ” of an Image},
  author={Brendan J. Frey and Nebojsa Jojic},
  year={2002}
}
Estimating and visualizing high-order statistics of multivariate data is important for analysis, synthesis and visualization in science and engineering. Often, data consists of measurements on an underlying domain, such as space or time. Examples include images, audio signals and text, where the domains are 2-D space, 1-D time and 1-D symbol index. We introduce a model called the “epitome” that can simultaneously represent multi-scale high-order statistics as a set of parameters on the same… CONTINUE READING
5 Citations
13 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 13 references

Intern

  • J. Portilla, E. P. Simoncelli
  • Journ. Comp. Vision 40, 49
  • 2000

J

  • J. Shi
  • Malik,IEEE Trans Patt. Anal. Mach. Intell. 222…
  • 2000
1 Excerpt

Science290

  • S. T. Roweis, L. K. Saul
  • 2323
  • 2000

Proc

  • W. Freeman, E. Pasztor
  • Internat. Conf. Comp. Vision , 1182
  • 1999
1 Excerpt

in M

  • R. M. Neal, G. E. Hinton
  • I. Jordan (ed) Learning in Graphical Models
  • 1998
1 Excerpt

IEEE Trans

  • M. Ostendorf, V. Digalakis, D. Kimball
  • Speech & Audio Proc. 4, 360
  • 1996
1 Excerpt

Image and Vis

  • A. Lanitis, C. J. Taylor, T. F. Cootes
  • Comput. 13, 393
  • 1995

Neural Comput

  • A. J. Bell, T. J. Sejnowski
  • 7, 1129
  • 1995

in C

  • D. Mumford
  • Koch, J. Davis (eds) Large-Scale Theories of the…
  • 1994
1 Excerpt

Similar Papers

Loading similar papers…