3449 search results - page 507 / 690 » A Framework for Multiple-Instance Learning |
176
click to vote
ICCV
2007
IEEE
16 years 9 months ago
2007
IEEE
Recent work in object categorization often uses local image descriptors such as SIFT to learn and detect object categories. Such descriptors explicitly code local appearance and h...
170
click to vote
ICCV
2005
IEEE
16 years 8 months ago
2005
IEEE
Many computer vision algorithms limit their performance by ignoring the underlying 3D geometric structure in the image. We show that we can estimate the coarse geometric propertie...
144
click to vote
ICIP
2005
IEEE
16 years 8 months ago
2005
IEEE
In this paper, we present a novel learning based framework for performing super-resolution using multiple images. We model the image as an undirected graphical model over image pa...
164
click to vote
ICIP
2003
IEEE
16 years 8 months ago
2003
IEEE
We propose an information-theoretic method for multi-phase image segmentation, in an active contour-based framework. Our approach is based on nonparametric density estimates, and ...
168
click to vote
ICPR
2008
IEEE
16 years 8 months ago
2008
IEEE
As an emerging human-computer interaction approachvision based hand interaction is more natural and efficient. Howeverin order to achieve high accuracy, most of the existing hand ...