2903 search results - page 232 / 581 » The Dark Side of Object Learning: Learning Objects |
127
click to vote
NIPS
2007
15 years 5 months ago
2007
The learning of probabilistic models with many hidden variables and nondecomposable dependencies is an important and challenging problem. In contrast to traditional approaches bas...
140
click to vote
VISAPP
2008
15 years 5 months ago
2008
In this paper we propose a method for continuous learning of simple visual concepts. The method continuously associates words describing observed scenes with automatically extracte...
154
click to vote
ESANN
2001
15 years 5 months ago
2001
Time varying environments or model selection problems lead to crucial dilemmas in identification and control science. In this paper, we propose a modular prediction scheme consisti...
132
click to vote
PR
2006
15 years 4 months ago
2006
Choosing appropriate values for kernel parameters is one of the key problems in many kernel-based methods because the values of these parameters have significant impact on the per...
119
click to vote
CVPR
2003
IEEE
16 years 6 months ago
2003
IEEE
For purpose of object recognition, we learn one discriminative classifier based on one prototype, using shape context distances as the feature vector. From multiple prototypes, th...