126
click to vote
CVPR
2004
IEEE
16 years 5 months ago
2004
IEEE
In this paper we present an automatic method for calibrating a network of cameras from only silhouettes. This is particularly useful for shape-from-silhouette or visual-hull syste...
143
click to vote
CVPR
2004
IEEE
16 years 5 months ago
2004
IEEE
We describe a method for obtaining the principal objects, characters and scenes in a video by measuring the reoccurrence of spatial configurations of viewpoint invariant features....
133
Voted
CVPR
2004
IEEE
16 years 5 months ago
2004
IEEE
Invariant features or operators are often used to shield the recognition process from the effect of "nuisance" parameters, such as rotations, foreshortening, or illumina...
148
click to vote
CVPR
2004
IEEE
16 years 5 months ago
2004
IEEE
We pose the problem of 3D human tracking as one of inference in a graphical model. Unlike traditional kinematic tree representations, our model of the body is a collection of loos...
157
click to vote
CVPR
2004
IEEE
16 years 5 months ago
2004
IEEE
We present Propagation Networks (P-Nets), a novel approach for representing and recognizing sequential activities that include parallel streams of action. We represent each activi...