107 search results - page 10 / 22 » Learning to Track Objects Through Unobserved Regions |
TSMC
2008
13 years 7 months ago
2008
Sensor networks are widely used in monitoring and tracking a large number of objects. Without prior knowledge on the dynamics of object distribution, their density estimation could...
WSCG
2004
13 years 8 months ago
2004
This paper presents a robust and reconfigurable object tracker that integrates multiple visual features from multiple views. The tandem modular architecture stepwise refines the e...
CIKM
2010
Springer
13 years 6 months ago
2010
Springer
We consider the problem of learning to rank relevant and novel documents so as to directly maximize a performance metric called Expected Global Utility (EGU), which has several de...
CVPR
2009
IEEE
15 years 2 months ago
2009
IEEE
Several recently-proposed architectures for highperformance
object recognition are composed of two main
stages: a feature extraction stage that extracts locallyinvariant
feature...
CVPR
2008
IEEE
14 years 9 months ago
2008
IEEE
For a large class of applications, there is time to train the system. In this paper, we propose a learning-based approach to patch perspective rectification, and show that it is b...