CVPR
2001
IEEE
16 years 2 months ago
2001
IEEE
Bayesian approaches to supervised learning use priors on the classifier parameters. However, few priors aim at achieving "sparse" classifiers, where irrelevant/redundant...
69
Voted
CVPR
2001
IEEE
16 years 2 months ago
2001
IEEE
CVPR
2001
IEEE
16 years 2 months ago
2001
IEEE
134
click to vote
CVPR
2001
IEEE
16 years 2 months ago
2001
IEEE
Isometric surfaces share the same geometric structure also known as the `first fundamental form'. For example, all possible bending of a given surface, that include all lengt...
115
Voted
CVPR
2001
IEEE
16 years 2 months ago
2001
IEEE
A bugbear of uncalibrated stereo reconstruction is that cameras which deviate from the pinhole model have to be pre-calibrated in order to correct for nonlinear lens distortion. I...
73
Voted
CVPR
2001
IEEE
16 years 2 months ago
2001
IEEE
100
click to vote
CVPR
2001
IEEE
16 years 2 months ago
2001
IEEE
Accurate estimation of effective camera focal length is crucial to the success of panoramic image stitching. Fast techniques for estimating the focal length exist, but are depende...
105
click to vote
CVPR
2001
IEEE
16 years 2 months ago
2001
IEEE
Representing images with layers has many important applications, such as video compression, motion analysis, and 3D scene analysis. This paper presents an approach to reliably ext...
118
Voted
CVPR
2001
IEEE
16 years 2 months ago
2001
IEEE
Particle filters have proven to be an effective tool for visual tracking in non-gaussian, cluttered environments. Conventional particle filters however do not scale to the problem...
76
Voted
CVPR
2001
IEEE
16 years 2 months ago
2001
IEEE