Sciweavers

208 search results - page 32 / 42
» A general boosting-based framework for active object recogni...
Sort
View
KDD
2006
ACM
180views Data Mining» more  KDD 2006»
14 years 8 months ago
Learning the unified kernel machines for classification
Kernel machines have been shown as the state-of-the-art learning techniques for classification. In this paper, we propose a novel general framework of learning the Unified Kernel ...
Steven C. H. Hoi, Michael R. Lyu, Edward Y. Chang
CVPR
2006
IEEE
14 years 9 months ago
Principled Hybrids of Generative and Discriminative Models
When labelled training data is plentiful, discriminative techniques are widely used since they give excellent generalization performance. However, for large-scale applications suc...
Julia A. Lasserre, Christopher M. Bishop, Thomas P...
IROS
2009
IEEE
201views Robotics» more  IROS 2009»
14 years 2 months ago
Modeling tool-body assimilation using second-order Recurrent Neural Network
— Tool-body assimilation is one of the intelligent human abilities. Through trial and experience, humans are capable of using tools as if they are part of their own bodies. This ...
Shun Nishide, Tatsuhiro Nakagawa, Tetsuya Ogata, J...
ICPR
2000
IEEE
13 years 11 months ago
Eigenfiltering for Flexible Eigentracking (EFE)
Traditional techniques for tracking non-rigid objects such as optical flow, correlation, active contours or color, can not deal with situations where image changes are not due to ...
Fernando De la Torre, Javier Melenchón, Jor...
ATAL
2008
Springer
13 years 9 months ago
A context-aware personal desktop assistant
We demonstrate an intelligent personal assistant agent that has been developed to aid a busy knowledge worker in managing time commitments and performing tasks. The PExA agent dra...
Hung Hai Bui, Federico Cesari, Daniel Elenius, Dav...