142
click to vote
ICPR
2006
IEEE
16 years 6 months ago
2006
IEEE
A novel background generation method based on nonparametric background model is presented for background subtraction. We introduce a new model, named as effect components descript...
ICPR
2006
IEEE
16 years 6 months ago
2006
IEEE
146
click to vote
ICPR
2006
IEEE
16 years 6 months ago
2006
IEEE
We present a dynamic inference algorithm in a globally parameterized nonlinear manifold and demonstrate it on the problem of visual tracking. An appearance manifold is usually non...
164
click to vote
ICPR
2006
IEEE
16 years 6 months ago
2006
IEEE
A new method for three dimensional (3D) genus-zero shape classification is proposed. It conformally maps a 3D mesh onto a unit sphere and uses normal vectors to generate a spheric...
154
click to vote
ICPR
2006
IEEE
16 years 6 months ago
2006
IEEE
Traditionally, the Universal Background Model (UBM) is viewed as the background model of the entire acoustic feature space. We propose a novel interpretation of the UBM model, and...
142
click to vote
ICPR
2006
IEEE
16 years 6 months ago
2006
IEEE
Latent Layout Analysis (LLA) is a novel unsupervised learning technique to discover objects in unseen images using a set of un-annotated training images. LLA defines a generative ...
156
click to vote
ICPR
2006
IEEE
16 years 6 months ago
2006
IEEE
Kernel Fisher Discriminant Analysis (KFDA) has achieved great success in pattern recognition recently. However, the training process of KFDA is too time consuming (even intractabl...
114
click to vote
ICPR
2006
IEEE
16 years 6 months ago
2006
IEEE
Although detecting text lines in machine printed documents is typically considered a solved problem, it is still a challenge to segment handwritten text lines in the general sense...
129
click to vote
ICPR
2006
IEEE
16 years 6 months ago
2006
IEEE
This paper investigates the problem of incorporating auxiliary information (e.g. pitch) for speech recognition using dynamic Bayesian networks (DBNs). Previous works usually model...
156
click to vote
ICPR
2006
IEEE
16 years 6 months ago
2006
IEEE
We aim to improve the accuracy of handwritten Chinese character recognition using two advanced techniques: discriminative feature extraction (DFE) and discriminative learning quad...