149
Voted
CVPR
2009
IEEE
16 years 9 months ago
2009
IEEE
Latent Variable Models (LVM), like the Shared-GPLVM
and the Spectral Latent Variable Model, help mitigate over-
fitting when learning discriminative methods from small or
modera...
134
Voted
CVPR
2009
IEEE
16 years 9 months ago
2009
IEEE
Image parsing remains difficult due to the need to combine
local and contextual information when labeling a
scene. We approach this problem by using the epitome as a
prior over ...
117
click to vote
CVPR
2009
IEEE
16 years 9 months ago
2009
IEEE
Most modern computer vision systems for high-level
tasks, such as image classification, object recognition and
segmentation, are based on learning algorithms that are
able to se...
102
click to vote
CVPR
2009
IEEE
16 years 9 months ago
2009
IEEE
Segmenting images into distinct material types is a very useful capability. Most work in image segmentation addresses the case where only a single image is available. Some methods ...
108
Voted
CVPR
2009
IEEE
16 years 9 months ago
2009
IEEE
In this paper, we address the complex problem of rapid modeling
of large-scale areas and present a novel approach for the automatic
reconstruction of cities from remote sensor da...
116
Voted
CVPR
2009
IEEE
16 years 9 months ago
2009
IEEE
We propose a method based on sparse representation
(SR) to cluster data drawn from multiple low-dimensional
linear or affine subspaces embedded in a high-dimensional
space. Our ...
122
click to vote
CVPR
2009
IEEE
16 years 9 months ago
2009
IEEE
Active contours is a popular technique for image segmentation.
However, active contour tend to converge to the
closest local minimum of its energy function and often requires
a ...
134
click to vote
CVPR
2009
IEEE
16 years 9 months ago
2009
IEEE
The visual world demonstrates organized spatial patterns,
among objects or regions in a scene, object-parts
in an object, and low-level features in object-parts. These
classes o...
140
click to vote
CVPR
2009
IEEE
16 years 9 months ago
2009
IEEE
In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
118
Voted
CVPR
2009
IEEE
16 years 9 months ago
2009
IEEE
In this paper, we wish to build a high quality database of
images depicting scenes, along with their real-world threedimensional
(3D) coordinates. Such a database is useful
for ...