83 search results - page 5 / 17 » A Discriminative Global Training Algorithm for Statistical M... |
117
click to vote
IJCV
2012
13 years 3 months ago
2012
Abstract Image alignment in the presence of non-rigid distortions is a challenging task. Typically, this involves estimating the parameters of a dense deformation field that warps...
126
click to vote
ICML
2009
IEEE
16 years 2 months ago
2009
IEEE
In this paper, we investigate a simple, mistakedriven learning algorithm for discriminative training of continuous density hidden Markov models (CD-HMMs). Most CD-HMMs for automat...
COLING
1992
15 years 2 months ago
1992
In this paper, a discrimination and robusmess oriented adaptive learning procedure is proposed to deal with the task of syntactic ambiguity resolution. Owing to the problem of ins...
105
click to vote
TASLP
2008
15 years 1 months ago
2008
This paper presents a novel online relevant set algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the glob...
104
click to vote
ICCV
2003
IEEE
16 years 3 months ago
2003
IEEE
Inpainting is the problem of filling-in holes in images. Considerable progress has been made by techniques that use the immediate boundary of the hole and some prior information o...