ICCV
2009
IEEE
15 years 6 months ago
2009
IEEE
This paper is focused on the Co-segmentation problem
[1] – where the objective is to segment a similar object from
a pair of images. The background in the two images may be
ar...
ICCV
2009
IEEE
15 years 6 months ago
2009
IEEE
Object class models trained on hundreds or thousands of
images have shown to enable robust detection. Transferring
knowledge from such models to new object classes trained
from ...
ICCV
2009
IEEE
15 years 6 months ago
2009
IEEE
Mean shift clustering is a powerful unsupervised data
analysis technique which does not require prior knowledge
of the number of clusters, and does not constrain the shape
of th...
ICCV
2009
IEEE
15 years 6 months ago
2009
IEEE
Image auto-annotation is an important open problem in
computer vision. For this task we propose TagProp, a discriminatively
trained nearest neighbor model. Tags of test
images a...
ICCV
2009
IEEE
15 years 6 months ago
2009
IEEE
We consider a class of region-based energies for image
segmentation and inpainting which combine region integrals
with curvature regularity of the region boundary. To
minimize s...
ICCV
2009
IEEE
15 years 6 months ago
2009
IEEE
Geometric rearrangement of images includes operations
such as image retargeting, inpainting, or object rearrangement.
Each such operation can be characterized by a shiftmap:
the...
ICCV
2009
IEEE
15 years 6 months ago
2009
IEEE
We present a novel approach for detecting global behaviour
anomalies in multiple disjoint cameras by learning
time delayed dependencies between activities cross camera
views. Sp...
ICCV
2009
IEEE
15 years 6 months ago
2009
IEEE
We study the problem of estimating the epipolar geometry
from apparent contours of smooth curved surfaces
with affine camera models. Since apparent contours are
viewpoint depend...
ICCV
2009
IEEE
15 years 6 months ago
2009
IEEE
Significant research has been devoted to detecting people
in images and videos. In this paper we describe a human detection
method that augments widely used edge-based features
...
ICCV
2009
IEEE
15 years 6 months ago
2009
IEEE
Similarity metrics that are learned from labeled training
data can be advantageous in terms of performance
and/or efficiency. These learned metrics can then be used
in conjuncti...