ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
We propose an unconventional but highly effective approach
to robust fitting of multiple structures by using statistical
learning concepts. We design a novel Mercer kernel
for t...
ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
We study the scenario of a multiview setting, where several
calibrated views of a textured object with known surface
geometry are available. The objective is to estimate a
diffu...
ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
In this paper we describe a method to learn parameters
which govern pedestrian motion by observing video
data. Our learning framework is based on variational
mode learning and a...
ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
The concept of graph cuts is by now a standard method
for all sorts of low level vision problems. Its popularity is
largely due to the fact that globally or near globally optimal...
ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
This paper proposes a new approach for video stabilization.
Most existing video stabilization methods adopt
a framework of three steps, motion estimation, motion compensation
an...
ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
This paper presents a target tracking framework for unstructured
crowded scenes. Unstructured crowded scenes
are defined as those scenes where the motion of a crowd
appears to b...
ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
This paper addresses the “boundary ownership” problem,
also known as the figure/ground assignment problem.
Estimating boundary ownerships is a key step in perceptual
organiz...
ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
When a curved mirror-like surface moves relative to its
environment, it induces a motion field—or specular flow—
on the image plane that observes it. This specular flow is
r...
ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
In this paper we present a combined approach for ob-
ject localization and classification. Our contribution is two-
fold. (a) A contextual combination of localization and clas-
...
ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
We present a system that can match and reconstruct 3D
scenes from extremely large collections of photographs such
as those found by searching for a given city (e.g., Rome) on
In...