Sciweavers

37 search results - page 5 / 8
» Discriminative versus generative parameter and structure lea...
Sort
View
PAMI
2011
12 years 10 months ago
Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin
—We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden condi...
Yang Wang 0003, Greg Mori
ICDAR
2009
IEEE
14 years 2 months ago
Unsupervised Selection and Discriminative Estimation of Orthogonal Gaussian Mixture Models for Handwritten Digit Recognition
The problem of determining the appropriate number of components is important in finite mixture modeling for pattern classification. This paper considers the application of an unsu...
Xuefeng Chen, Xiabi Liu, Yunde Jia
IJAR
2010
152views more  IJAR 2010»
13 years 6 months ago
Structural-EM for learning PDG models from incomplete data
Probabilistic Decision Graphs (PDGs) are a class of graphical models that can naturally encode some context specific independencies that cannot always be efficiently captured by...
Jens D. Nielsen, Rafael Rumí, Antonio Salme...
CVPR
1999
IEEE
14 years 9 months ago
Time-Series Classification Using Mixed-State Dynamic Bayesian Networks
We present a novel mixed-state dynamic Bayesian network (DBN) framework for modeling and classifying timeseries data such as object trajectories. A hidden Markov model (HMM) of di...
Vladimir Pavlovic, Brendan J. Frey, Thomas S. Huan...
CVPR
2009
IEEE
1390views Computer Vision» more  CVPR 2009»
15 years 2 months ago
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
In this paper we present a method for learning classspecific features for recognition. Recently a greedy layerwise procedure was proposed to initialize weights of deep belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...