13476 search results - page 2608 / 2696 » Learning from Streams |
117
Voted
CVPR
2007
IEEE
16 years 5 months ago
2007
IEEE
A large family of algorithms for dimensionality reduction end with solving a Trace Ratio problem in the form of arg maxW Tr(WT SpW)/Tr(WT SlW)1 , which is generally transformed in...
153
Voted
CVPR
2007
IEEE
16 years 5 months ago
2007
IEEE
The appearance of a scene is a function of the scene contents, the lighting, and the camera pose. A set of n-pixel images of a non-degenerate scene captured from different perspec...
143
Voted
CVPR
2008
IEEE
16 years 5 months ago
2008
IEEE
Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
124
Voted
CVPR
2008
IEEE
16 years 5 months ago
2008
IEEE
Studies support the need for high resolution imagery to identify persons in surveillance videos[13]. However, the use of telephoto lenses sacrifices a wider field of view and ther...
139
Voted
ICCV
2007
IEEE
16 years 5 months ago
2007
IEEE
Boosting has been widely applied in computer vision, especially after Viola and Jones's seminal work [23]. The marriage of rectangular features and integral-imageenabled fast...