39 search results - page 4 / 8 » Jensen-Shannon Boosting Learning for Object Recognition |
ICPR
2004
IEEE
14 years 7 months ago
2004
IEEE
: A new method is presented to learn object categories from unlabeled and unsegmented images for generic object recognition. We assume that each object can be characterized by a se...
CVPR
2010
IEEE
13 years 6 months ago
2010
IEEE
Transfer learning allows leveraging the knowledge of source domains, available a priori, to help training a classifier for a target domain, where the available data is scarce. Th...
CIVR
2008
Springer
13 years 8 months ago
2008
Springer
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...
ICCV
2007
IEEE
14 years 8 months ago
2007
IEEE
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
ECCV
2010
Springer
13 years 11 months ago
2010
Springer
Many learning tasks for computer vision problems can be described by multiple views or multiple features. These views can be exploited in order to learn from unlabeled data, a.k.a....