3449 search results - page 47 / 690 » A Framework for Multiple-Instance Learning |
ICIP
2005
IEEE
14 years 9 months ago
2005
IEEE
We present a novel and intuitive framework for building modular vision systems for complex tasks such as surveillance applications. Inspired by graphical models, especially factor...
ICIG
2009
IEEE
14 years 2 months ago
2009
IEEE
Classifying natural scenes into semantic categories has always been a challenging task. So far, many works in this field are primarily intended for single label classification, wh...
JMLR
2006
13 years 7 months ago
2006
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...
PR
2007
13 years 7 months ago
2007
In this paper, we propose a robust incremental learning framework for accurate skin region segmentation in real-life images. The proposed framework is able to automatically learn ...
NIPS
2007
13 years 9 months ago
2007
Learning the common structure shared by a set of supervised tasks is an important practical and theoretical problem. Knowledge of this structure may lead to better generalization ...