5082 search results - page 444 / 1017 » Actionable Information in Vision |
201
click to vote
ICCV
2009
IEEE
17 years 3 hour 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 ...
213
click to vote
ICCV
2009
IEEE
17 years 3 hour ago
2009
IEEE
Clustering performance can often be greatly improved by
leveraging side information. In this paper, we consider constrained
clustering with pairwise constraints, which specify
s...
178
Voted
ICCV
2009
IEEE
17 years 3 hour ago
2009
IEEE
In this paper, we introduce a new approach for modeling
visual context. For this purpose, we consider the leaves of a
hierarchical segmentation tree as elementary units. Each
le...
176
click to vote
CVPR
1999
IEEE
16 years 9 months ago
1999
IEEE
The main question we address is: what is the minimal information required to generate closed, non-intersecting planar boundaries? For this paper we restrict ‘shape’ to this mea...
174
click to vote
CVPR
2000
IEEE
16 years 9 months ago
2000
IEEE
A novel algorithm for motion segmentation is proposed. The algorithm uses the fact that shape of an object with homogeneous motion is represented as 4 dimensional linear space. Th...