CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
We propose an approach to restore severely degraded
document images using a probabilistic context model. Un-
like traditional approaches that use previously learned
prior models...
CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
We study the problem of object classification when training
and test classes are disjoint, i.e. no training examples of
the target classes are available. This setup has hardly be...
CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
In factorization approaches to nonrigid structure from
motion, the 3D shape of a deforming object is usually modeled
as a linear combination of a small number of basis
shapes. T...
CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
This paper addresses the problem of establishing correspondences
between two sets of visual features using
higher-order constraints instead of the unary or pairwise
ones used in...
CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
This paper addresses the problem of characterizing
a general class of cameras under reasonable, “linear”
assumptions. Concretely, we use the formalism and
terminology of cla...
CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
We propose an algorithm that simultaneously extracts
disparities and alpha matting information given a stereo
image pair. Our method divides the reference image into
a set of ov...
CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
We study the cosegmentation problem where the objective
is to segment the same object (i.e., region) from a pair
of images. The segmentation for each image can be cast
using a p...
CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
The literature currently provides two ways to establish
point correspondences between images with moving objects.
On one side, there are energy minimization methods
that yield v...
CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
We present a discriminative Hough transform based ob-
ject detector where each local part casts a weighted vote for
the possible locations of the object center. We show that the
...
CVPR
2009
IEEE
15 years 6 months ago
2009
IEEE
Contemporary face recognition algorithms rely on precise
localization of keypoints (corner of eye, nose etc.). Unfortunately,
finding keypoints reliably and accurately remains
a...