6113 search results - page 104 / 1223 » Learning Features for Tracking |
112
Voted
ICPR
2006
IEEE
16 years 3 months ago
2006
IEEE
Laser based people tracking systems have been developed for mobile robotic or intelligent surveillance areas. Existing systems rely on laser point clustering to extract object loc...
DAGM
2007
Springer
15 years 8 months ago
2007
Springer
Typical tracking algorithms exploit temporal coherence, in the sense of expecting only small object motions. Even without exact knowledge of the scene, additional spatial coherence...
120
click to vote
ICIP
2010
IEEE
15 years 8 days ago
2010
IEEE
The compression of video can reduce the accuracy of post-compression tracking algorithms. This is problematic for centralized applications such as traffic surveillance systems, wh...
150
click to vote
CVPR
2005
IEEE
16 years 4 months ago
2005
IEEE
We develop an object classification method that can learn a novel class from a single training example. In this method, experience with already learned classes is used to facilita...
135
Voted
ICML
2007
IEEE
16 years 3 months ago
2007
IEEE
In many prediction tasks, selecting relevant features is essential for achieving good generalization performance. Most feature selection algorithms consider all features to be a p...