Sciweavers

216 search results - page 32 / 44
» Handwritten Character Recognition Based on Structural Charac...
Sort
View
JMLR
2010
169views more  JMLR 2010»
14 years 4 months ago
Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images
Deep belief nets have been successful in modeling handwritten characters, but it has proved more difficult to apply them to real images. The problem lies in the restricted Boltzma...
Marc'Aurelio Ranzato, Alex Krizhevsky, Geoffrey E....
ICDAR
1999
IEEE
15 years 2 months ago
Combining Classifiers based on Confidence Values
This paper describes our investigation into the neural gas (NG) network algorithm and the hierarchical overlapped architecture (HONG) which we have built by retaining the essence ...
Ajantha S. Atukorale, Ponnuthurai N. Suganthan
MLMI
2004
Springer
15 years 3 months ago
A Hierarchical System for Recognition, Tracking and Pose Estimation
This paper presents a new system for recognition, tracking and pose estimation of people in video sequences. It is based on the wavelet transform from the upper body part and uses ...
Philipp Zehnder, Esther Koller-Meier, Luc J. Van G...
CVPR
2008
IEEE
14 years 11 months ago
Classification via semi-Riemannian spaces
In this paper, we develop a geometric framework for linear or nonlinear discriminant subspace learning and classification. In our framework, the structures of classes are conceptu...
Deli Zhao, Zhouchen Lin, Xiaoou Tang
JMLR
2010
185views more  JMLR 2010»
14 years 4 months ago
Efficient Heuristics for Discriminative Structure Learning of Bayesian Network Classifiers
We introduce a simple order-based greedy heuristic for learning discriminative structure within generative Bayesian network classifiers. We propose two methods for establishing an...
Franz Pernkopf, Jeff A. Bilmes