1585 search results - page 124 / 317 » Using a Non-prior Training Active Feature Model |
146
click to vote
CVPR
2010
IEEE
16 years 26 days ago
2010
IEEE
In matching tasks in computer vision, and particularly in real-time tracking from video, there are generally strong priors available on absolute and relative correspondence locati...
119
click to vote
ICASSP
2009
IEEE
15 years 11 months ago
2009
IEEE
We describe a new GMM-UBM speaker recognition system that uses standard cepstral features, but selects different frames of speech for different subsystems. Subsystems, or “const...
167
click to vote
PRICAI
2004
Springer
15 years 9 months ago
2004
Springer
Currently, most human action recognition systems are trained with feature sets that have no missing data. Unfortunately, the use of human pose estimation models to provide more des...
143
click to vote
CVPR
2009
IEEE
16 years 11 months ago
2009
IEEE
This article presents a general approach for the active
stereo tracking of multiple moving targets. The problem is
formulated on the plane, where cameras are modeled as
”line ...
133
click to vote
TIP
2008
15 years 4 months ago
2008
Abstract--In this paper, we propose a natural framework that allows any region-based segmentation energy to be re-formulated in a local way. We consider local rather than global im...