274 search results - page 9 / 55 » Activity Recognition from Sparsely Labeled Data Using Multi-... |
MM
2006
ACM
14 years 1 months ago
2006
ACM
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
ICMLA
2007
13 years 8 months ago
2007
We apply a new active learning formulation to the problem of learning medical concepts from unstructured text. The new formulation is based on maximizing the mutual information th...
COLING
2008
13 years 8 months ago
2008
Active learning is a proven method for reducing the cost of creating the training sets that are necessary for statistical NLP. However, there has been little work on stopping crit...
ICIP
2010
IEEE
13 years 5 months ago
2010
IEEE
Face recognition (FR) is an active yet challenging topic in computer vision applications. As a powerful tool to represent high dimensional data, recently sparse representation bas...
CVPR
2010
IEEE
14 years 3 months ago
2010
IEEE
A central problem in the analysis of motion capture (Mo-
Cap) data is how to decompose motion sequences into primitives.
Ideally, a description in terms of primitives should
fac...