Sciweavers

571 search results - page 54 / 115
» One person labels one million images
Sort
View
VISAPP
2010
13 years 8 months ago
Inverse Problems in Imaging and Computer Vision - From Regularization Theory to Bayesian Inference
phies are also mentioned and a common mathematical abstraction for all these inverses problems will be presented. By focusing on a simple linear forward model, first a synthetic an...
Ali Mohammad-Djafari
ICB
2009
Springer
184views Biometrics» more  ICB 2009»
14 years 5 months ago
An Analysis-by-Synthesis Method for Heterogeneous Face Biometrics
Face images captured in different spectral bands, e.g. , in visual (VIS) and near infrared (NIR), are said to be heterogeneous. Although a person’s face looks different in hetero...
Rui Wang, Jimei Yang, Dong Yi, Stan Z. Li
FGR
2004
IEEE
94views Biometrics» more  FGR 2004»
14 years 2 months ago
A Symmetric Transformation for LDA-based Face Verification
One of the major problem in face verification is to deal with a few number of images per person to train the system. A solution to that problem is to generate virtual samples from...
Sébastien Marcel
SDM
2004
SIAM
187views Data Mining» more  SDM 2004»
14 years 7 days ago
Class-Specific Ensembles for Active Learning
In many real-world tasks of image classification, limited amounts of labeled data are available to train automatic classifiers. Consequently, extensive human expert involvement is...
Amit Mandvikar, Huan Liu
CVPR
2004
IEEE
15 years 26 days ago
A Graphical Model Framework for Coupling MRFs and Deformable Models
This paper proposes a new framework for image segmentation based on the integration of MRFs and deformable models using graphical models. We first construct a graphical model to r...
Rui Huang, Vladimir Pavlovic, Dimitris N. Metaxas