318 search results - page 61 / 64 » Computing by observing |
166
click to vote
CVPR
2007
IEEE
16 years 7 months ago
2007
IEEE
Considerable advances have been made in learning to recognize and localize visual object classes. Simple bag-offeature approaches label each pixel or patch independently. More adv...
143
click to vote
CVPR
2007
IEEE
16 years 7 months ago
2007
IEEE
Much of the research on video-based human motion capture assumes the body shape is known a priori and is represented coarsely (e.g. using cylinders or superquadrics to model limbs...
135
click to vote
CVPR
2008
IEEE
16 years 7 months ago
2008
IEEE
In the last decade, graph-cut optimization has been popular for a variety of pixel labeling problems. Typically graph-cut methods are used to incorporate a smoothness prior on a l...
172
click to vote
CVPR
2008
IEEE
16 years 7 months ago
2008
IEEE
To learn a new visual category from few examples, prior knowledge from unlabeled data as well as previous related categories may be useful. We develop a new method for transfer le...
140
click to vote
CVPR
2010
IEEE
16 years 1 months ago
2010
IEEE
Detecting an object part relies on two sources of information - the appearance of the part itself, and the context supplied by surrounding parts. In this paper we consider problem...