Sciweavers

4377 search results - page 514 / 876
» Mass problems and randomness
Sort
View
TIT
1998
102views more  TIT 1998»
15 years 6 months ago
On Characterization of Entropy Function via Information Inequalities
—Given n discrete random variables = fX1;111; Xng, associated with any subset of f1; 2; 111; ng, there is a joint entropy H(X ) where X = fXi:i 2 g. This can be viewed as a f...
Zhen Zhang, Raymond W. Yeung
CVPR
2009
IEEE
17 years 2 months ago
Half-integrality based algorithms for Cosegmentation of Images
We study the cosegmentation problem where the objective is to segment the same object (i.e., region) from a pair of images. The segmentation for each image can be cast using a p...
Chuck R. Dyer, Lopamudra Mukherjee, Vikas Singh
CVPR
2009
IEEE
1382views Computer Vision» more  CVPR 2009»
17 years 1 months ago
Super-Resolution via Recapture and Bayesian Effect Modeling
This paper presents Bayesian edge inference (BEI), a single-frame super-resolution method explicitly grounded in Bayesian inference that addresses issues common to existing meth...
Bryan S. Morse, Dan Ventura, Kevin D. Seppi, Neil ...
ICCV
2009
IEEE
16 years 11 months ago
Higher-Order Gradient Descent by Fusion-Move Graph Cut
Markov Random Field is now ubiquitous in many formulations of various vision problems. Recently, optimization of higher-order potentials became practical using higherorder graph...
Hiroshi Ishikawa
CVPR
2003
IEEE
16 years 8 months ago
Bootstrapping SVM Active Learning by Incorporating Unlabelled Images for Image Retrieval
The performance of image retrieval with SVM active learning is known to be poor when started with few labelled images only. In this paper, the problem is solved by incorporating t...
Lei Wang, Kap Luk Chan, Zhihua Zhang