274 search results - page 40 / 55 » Activity Recognition from Sparsely Labeled Data Using Multi-... |
ACCV
2010
Springer
13 years 2 months ago
2010
Springer
Abstract. We present a novel approach to detect and classify rare behaviours which are visually subtle and occur sparsely in the presence of overwhelming typical behaviours. We tre...
ECCV
2008
Springer
14 years 9 months ago
2008
Springer
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...
ICASSP
2010
IEEE
13 years 7 months ago
2010
IEEE
Supervised learning uses a training set of labeled examples to compute a classifier which is a mapping from feature vectors to class labels. The success of a learning algorithm i...
MVA
2007
13 years 8 months ago
2007
For a social robot, the ability of learning tasks via human demonstration is very crucial. But most current approaches suffer from either the demanding of the huge amount of label...
IJCV
2008
13 years 7 months ago
2008
We present a new data set encoding localized semantics for 1014 images and a methodology for using this kind of data for recognition evaluation. This methodology establishes protoc...