1585 search results - page 44 / 317 » Using a Non-prior Training Active Feature Model |
117
click to vote
NAACL
2004
15 years 5 months ago
2004
Supervised estimation methods are widely seen as being superior to semi and fully unsupervised methods. However, supervised methods crucially rely upon training sets that need to ...
171
click to vote
EMNLP
2011
14 years 3 months ago
2011
Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...
119
click to vote
IJCNN
2007
IEEE
15 years 10 months ago
2007
IEEE
— A spiking neural network model is used to identify characters in a character set. The network is a two layered structure consisting of integrate-and-fire and active dendrite n...
147
click to vote
DAGM
2006
Springer
15 years 7 months ago
2006
Springer
Abstract. Active Shape Models are commonly used to recognize and locate different aspects of known rigid objects. However, they require an off-line learning stage, such that the ex...
134
click to vote
CVPR
2005
IEEE
16 years 6 months ago
2005
IEEE
This paper addresses the problem of learning and recognizing human activities of daily living (ADL), which is an important research issue in building a pervasive and smart environ...