CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
Matching based on local brightness is quite limited, because
small changes on local appearance invalidate the
constancy in brightness. The root of this limitation is its
treatme...
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
Accurate denition of similarity measure is a key component
in image registration. Most commonly used intensitybased
similarity measures rely on the assumptions of independence
...
CVPR
2009
IEEE
14 years 11 months ago
2009
IEEE
State of the art methods for image and object re-
trieval exploit both appearance (via visual words) and
local geometry (spatial extent, relative pose). In large
scale problems,...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. T...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
This paper deals with the problem of tracking multiple targets in a distributed network of self-configuring pan-tilt-zoom cameras. We focus on applications where events unfold over...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
Local image descriptors that are highly discriminative,
computational efficient, and with low storage footprint have
long been a dream goal of computer vision research. In this
...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
The matching and retrieval of 2D shapes is an important
challenge in computer vision. A large number of shape
similarity approaches have been developed, with the main
focus bein...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
In this paper, we propose a novel approach for learning generic visual vocabulary. We use diffusion maps to au-tomatically learn a semantic visual vocabulary from ab-undant quantiz...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
In this paper, we consider the problem of categorizing
videos of dynamic textures under varying view-point. We
propose to model each video with a collection of Linear
Dynamics S...
CVPR
2009
IEEE
14 years 12 months ago
2009
IEEE
In this work we present an approach for markerless
motion capture (MoCap) of articulated objects, which are
recorded with multiple unsynchronized moving cameras.
Instead of usin...