Sciweavers

117 search results - page 12 / 24
» Manifold Based Local Classifiers: Linear and Nonlinear Appro...
Sort
View
ICCV
2009
IEEE
1038views Computer Vision» more  ICCV 2009»
16 years 2 months ago
Combining efficient object localization and image classification
In this paper we present a combined approach for ob- ject localization and classification. Our contribution is two- fold. (a) A contextual combination of localization and clas- ...
Hedi Harzallah, Frederic Jurie, Cordelia Schmid
ICVGIP
2008
14 years 11 months ago
Monocular Depth by Nonlinear Diffusion
Following the phenomenological approach of gestaltists, sparse monocular depth cues such as T- and X-junctions and the local convexity are crucial to identify the shape and depth ...
Jean-Michel Morel, Philippe Salembier
CVPR
2008
IEEE
14 years 11 months ago
Classification via semi-Riemannian spaces
In this paper, we develop a geometric framework for linear or nonlinear discriminant subspace learning and classification. In our framework, the structures of classes are conceptu...
Deli Zhao, Zhouchen Lin, Xiaoou Tang
AUTOMATICA
2005
136views more  AUTOMATICA 2005»
14 years 9 months ago
Conjugate Lyapunov functions for saturated linear systems
Based on a recent duality theory for linear differential inclusions (LDIs), the condition for stability of an LDI in terms of one Lyapunov function can be easily derived from that...
Tingshu Hu, Rafal Goebel, Andrew R. Teel, Zongli L...
TMI
1998
181views more  TMI 1998»
14 years 9 months ago
Image Contrast Enhancement Based on a Histogram Transformation of Local Standard Deviation
Abstract— The adaptive contrast enhancement (ACE) algorithm, which uses contrast gains (CG’s) to adjust the highfrequency components of images, is a well-known technique for me...
Dah-Chung Chang, Wen-Rong Wu