3449 search results - page 419 / 690 » A Framework for Multiple-Instance Learning |
172
click to vote
NAACL
2010
15 years 4 months ago
2010
Perceptron training is widely applied in the natural language processing community for learning complex structured models. Like all structured prediction learning frameworks, the ...
213
click to vote
SEAL
2010
Springer
15 years 4 months ago
2010
Springer
Abstract. Mainstream surrogate approaches for multi-objective problems build one approximation for each objective. Mono-surrogate approaches instead aim at characterizing the Paret...
172
Voted
SIGDIAL
2010
15 years 4 months ago
2010
Spoken dialogue management strategy optimization by means of Reinforcement Learning (RL) is now part of the state of the art. Yet, there is still a clear mismatch between the comp...
141
Voted
EMNLP
2009
15 years 3 months ago
2009
Traditional learning-based coreference resolvers operate by training a mentionpair classifier for determining whether two mentions are coreferent or not. Two independent lines of ...
157
Voted
ICCV
2009
IEEE
15 years 3 months ago
2009
IEEE
We present a system that constructs "implicit shape models" for classes of rigid 3D objects and utilizes these models to estimating the pose of class instances in single...