Sciweavers

404 search results - page 16 / 81
» Threads Yield Continuations
Sort
View
ECCV
1998
Springer
14 years 1 months ago
Continuous Audio-Visual Speech Recognition
The Multi-Stream automatic speech recognition approach was investigated in this work as a framework for Audio-Visual data fusion and speech recognition. This method presents many ...
Juergen Luettin, Stéphane Dupont
ECCV
2008
Springer
14 years 11 months ago
Continuous Energy Minimization Via Repeated Binary Fusion
Abstract. Variational problems, which are commonly used to solve lowlevel vision tasks, are typically minimized via a local, iterative optimization strategy, e.g. gradient descent....
Werner Trobin, Thomas Pock, Daniel Cremers, Horst ...
ICPR
2008
IEEE
14 years 10 months ago
Rapid signer adaptation for continuous sign language recognition using a combined approach of eigenvoices, MLLR, and MAP
Current sign language recognition systems are still designed for signer-dependent operation only and thus suffer from the problem of interpersonal variability in production. Appli...
Christoph Blömer, Karl-Friedrich Kraiss, Ulri...
ICML
2009
IEEE
14 years 9 months ago
Matrix updates for perceptron training of continuous density hidden Markov models
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...
Chih-Chieh Cheng, Fei Sha, Lawrence K. Saul
DICTA
2003
13 years 10 months ago
Globally Optimal Surfaces by Continuous Maximal Flows
Abstract. In this paper we solve the problem of computing exact continuous optimal curves and surfaces for image segmentation and 3D reconstruction, using a maximal flow approach ...
Ben Appleton, Hugues Talbot