144 search results - page 16 / 29 » Learning in the Presence of Inaccurate Information |
CVPR
2003
IEEE
14 years 10 months ago
2003
IEEE
This paper studies the problem of combining region and boundary cues for natural image segmentation. We employ a large database of manually segmented images in order to learn an o...
ICML
2004
IEEE
14 years 9 months ago
2004
IEEE
In this paper we focus on the adaptation of boosting to grammatical inference. We aim at improving the performances of state merging algorithms in the presence of noisy data by us...
TREC
2004
13 years 9 months ago
2004
Our system for the Novelty Track at TREC 2004 looks beyond sentence boundaries as well as within sentences to identify novel, nonduplicative passages. It tries to identify text sp...
COLING
2002
13 years 8 months ago
2002
While Named Entity extraction is useful in many natural language applications, the coarse categories that most NE extractors work with prove insufficient for complex applications ...
HRI
2011
ACM
12 years 12 months ago
2011
ACM
In this paper, we present an approach to monitor human activities such as entry, exit and break times of people in a workplace environment. The companion robot then learns the use...