Sciweavers

193 search results - page 21 / 39
» An Alternative Model for Mixtures of Experts
Sort
View
NAACL
2003
15 years 3 months ago
Implicit Trajectory Modeling through Gaussian Transition Models for Speech Recognition
It is well known that frame independence assumption is a fundamental limitation of current HMM based speech recognition systems. By treating each speech frame independently, HMMs ...
Hua Yu, Tanja Schultz
IJCV
2002
133views more  IJCV 2002»
15 years 1 months ago
Probabilistic Tracking with Exemplars in a Metric Space
Abstract. A new, exemplar-based, probabilistic paradigm for visual tracking is presented. Probabilistic mechanisms are attractive because they handle fusion of information, especia...
Kentaro Toyama, Andrew Blake
ICASSP
2009
IEEE
15 years 8 months ago
Multi-view tracking of articulated human motion in silhouette and pose manifolds
This paper presents a multi-view articulated human motion tracking framework using particle filter with manifold learning through Gaussian process latent variable model. The dime...
Feng Guo, Gang Qian
NN
2010
Springer
225views Neural Networks» more  NN 2010»
15 years 8 days ago
Learning to imitate stochastic time series in a compositional way by chaos
This study shows that a mixture of RNN experts model can acquire the ability to generate sequences that are combination of multiple primitive patterns by means of self-organizing ...
Jun Namikawa, Jun Tani
IR
2002
15 years 1 months ago
Hierarchical Text Categorization Using Neural Networks
This paper presents the design and evaluation of a text categorization method based on the Hierarchical Mixture of Experts model. This model uses a divide and conquer principle to ...
Miguel E. Ruiz, Padmini Srinivasan