514 search results - page 80 / 103 » Contour-Based Learning for Object Detection |
ECCV
2010
Springer
14 years 25 days ago
2010
Springer
Abstract. We propose a novel method for unsupervised class segmentation on a set of images. It alternates between segmenting object instances and learning a class model. The method...
CVPR
2008
IEEE
14 years 9 months ago
2008
IEEE
The required amount of labeled training data for object detection and classification is a major drawback of current methods. Combining labeled and unlabeled data via semisupervise...
ICCV
2005
IEEE
14 years 9 months ago
2005
IEEE
In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...
CIDM
2007
IEEE
13 years 11 months ago
2007
IEEE
Kernel methods are effective approaches to the modeling of structured objects in learning algorithms. Their major drawback is the typically high computational complexity of kernel ...
ICRA
2008
IEEE
14 years 2 months ago
2008
IEEE
Abstract— We propose a novel online framework for detecting moving shadows in video sequences using statistical learning techniques. In this framework, Support Vector Machines ar...