2295 search results - page 256 / 459 » Learning Overcomplete Representations |
170
click to vote
PAMI
2008
15 years 6 months ago
2008
We introduce Gaussian process dynamical models (GPDMs) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensional motio...
182
click to vote
NAACL
2010
15 years 4 months ago
2010
We show that the automatically induced latent variable grammars of Petrov et al. (2006) vary widely in their underlying representations, depending on their EM initialization point...
177
click to vote
COLING
2010
15 years 1 months ago
2010
Lexicalized Well-Founded Grammar (LWFG) is a recently developed syntacticsemantic grammar formalism for deep language understanding, which balances expressiveness with provable le...
182
click to vote
EMNLP
2011
14 years 6 months ago
2011
We consider the problem of learning factored probabilistic CCG grammars for semantic parsing from data containing sentences paired with logical-form meaning representations. Tradi...
184
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
In many vision problems, rotation-invariant analysis is necessary or preferred. Popular solutions are mainly based on pose normalization or brute-force learning, neglecting the in...