|
Science 28 June 1996:
Vol. 272. no. 5270, pp. 1905 - 1909
DOI: 10.1126/science.272.5270.1905
|
|
Articles
Image Representations for Visual Learning
David Beymer
and
Tomaso Poggio
*
Computer vision researchers are developing new approaches to object
recognition and detection that are based almost directly on images and
avoid the use of intermediate three-dimensional models. Many of these
techniques depend on a representation of images that induces a linear
vector space structure and in principle requires dense feature
correspondence. This image representation allows the use of learning
techniques for the analysis of images (for computer vision) as well as
for the synthesis of images (for computer graphics).
The authors are in the Department of Brain and Cognitive Science,
Center for Biological and Computational Learning (CBCL) and Artificial
Intelligence Laboratory, Massachusetts Institute of Technology,
Cambridge, MA 02142, USA.
*
To whom correspondence should be addressed. E-mail:
tp{at}ai.mit.edu
THIS ARTICLE HAS BEEN CITED BY OTHER ARTICLES:
- Role of ordinal contrast relationships in face encoding.
- S. Gilad, M. Meng, and P. Sinha (2009)
PNAS
106, 5353-5358
| Abstract »
| Full Text »
| PDF »
- Visual Categorization and the Primate Prefrontal Cortex: Neurophysiology and Behavior.
- D. J. Freedman, M. Riesenhuber, T. Poggio, and E. K. Miller (2002)
J Neurophysiol
88, 929-941
| Abstract »
| Full Text »
| PDF »
- Categorical Representation of Visual Stimuli in the Primate Prefrontal Cortex.
- D. J. Freedman, M. Riesenhuber, T. Poggio, and E. K. Miller (2001)
Science
291, 312-316
| Abstract »
| Full Text »
- A Global Geometric Framework for Nonlinear Dimensionality Reduction.
- J. B. Tenenbaum, V. d. Silva, and J. C. Langford (2000)
Science
290, 2319-2323
| Abstract »
| Full Text »
- Nonlinear Dimensionality Reduction by Locally Linear Embedding.
- S. T. Roweis and L. K. Saul (2000)
Science
290, 2323-2326
| Abstract »
| Full Text »
