531 search results - page 99 / 107 » Using Photometric Invariants for 3D Object Recognition |
ICML
2010
IEEE
14 years 10 months ago
2010
IEEE
Many modern visual recognition algorithms incorporate a step of spatial `pooling', where the outputs of several nearby feature detectors are combined into a local or global `...
87
Voted
CVPR
2008
IEEE
15 years 11 months ago
2008
IEEE
In this paper, we propose a framework that fuses multiple features for improved action recognition in videos. The fusion of multiple features is important for recognizing actions ...
ICIAP
2007
ACM
15 years 9 months ago
2007
ACM
This work is about a novel methodology for window detection in urban environments and its multiple use in vision system applications. The presented method for window detection inc...
102
click to vote
SLSFS
2005
Springer
15 years 2 months ago
2005
Springer
We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns...
107
click to vote
ICCV
2001
IEEE
15 years 11 months ago
2001
IEEE
We prove that the set of all Lambertian reflectance functions (the mapping from surface normals to intensities) obtained with arbitrary distant light sources lies close to a 9D lin...