4660 search results - page 100 / 932 » Learning from imperfect data |
ICML
2007
IEEE
14 years 9 months ago
2007
IEEE
In many prediction tasks, selecting relevant features is essential for achieving good generalization performance. Most feature selection algorithms consider all features to be a p...
NIPS
1998
13 years 10 months ago
1998
We seek the scene interpretation that best explains image data. For example, we may want to infer the projected velocities (scene) which best explain two consecutive image frames ...
AAAI
2007
13 years 11 months ago
2007
The authors present TWIG, a visually grounded wordlearning system that uses its existing knowledge of vocabulary, grammar, and action schemas to help it learn the meanings of new ...
ECSQARU
2007
Springer
14 years 3 months ago
2007
Springer
Abstract. The Transferable Belief Model (TBM) relies on belief functions and enables one to represent and combine a variety of knowledge from certain up to ignorance as well as con...
CVPR
2003
IEEE
14 years 2 months ago
2003
IEEE
A “graphics for vision” approach is proposed to address the problem of reconstruction from a large and imperfect data set: reconstruction on demand by tensor voting, or ROD-TV...