Sciweavers

Share
CVPR
2008
IEEE
10 years 9 months ago
Semi-supervised boosting using visual similarity learning
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...
Christian Leistner, Helmut Grabner, Horst Bischof
CVPR
2007
IEEE
10 years 9 months ago
Learning Visual Representations using Images with Captions
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...
Ariadna Quattoni, Michael Collins, Trevor Darrell
CVPR
2006
IEEE
10 years 9 months ago
Semi-Supervised Classification Using Linear Neighborhood Propagation
We consider the general problem of learning from both labeled and unlabeled data. Given a set of data points, only a few of them are labeled, and the remaining points are unlabele...
Fei Wang, Changshui Zhang, Helen C. Shen, Jingdong...
CVPR
2005
IEEE
10 years 9 months ago
Semi-Supervised Cross Feature Learning for Semantic Concept Detection in Videos
For large scale automatic semantic video characterization, it is necessary to learn and model a large number of semantic concepts. But a major obstacle to this is the insufficienc...
Rong Yan, Milind R. Naphade
CVPR
2003
IEEE
10 years 9 months ago
Learning Bayesian Network Classifiers for Facial Expression Recognition using both Labeled and Unlabeled Data
Understanding human emotions is one of the necessary skills for the computer to interact intelligently with human users. The most expressive way humans display emotions is through...
Ira Cohen, Nicu Sebe, Fabio Gagliardi Cozman, Marc...
books