Sciweavers

145 search results - page 20 / 29
» Discriminative techniques for keyframe selection
Sort
View
ICDAR
2011
IEEE
13 years 9 months ago
A New Feature Optimization Method Based on Two-Directional 2DLDA for Handwritten Chinese Character Recognition
—LDA transformation is one of the popular feature dimension reduction techniques for the feature extraction in most handwritten Chinese characters recognition systems. The integr...
Xue Gao, Wenhuan Wen, Lianwen Jin
PRL
2010
181views more  PRL 2010»
14 years 8 months ago
Gait recognition without subject cooperation
The strength of gait, compared to other biometrics, is that it does not require cooperative subjects. Previoius gait recognition approaches were evaluated using a gallery set cons...
Khalid Bashir, Tao Xiang, Shaogang Gong
CVPR
2006
IEEE
15 years 11 months ago
Local Features, All Grown Up
We present a technique to adapt the domain of local features through the matching process to augment their discriminative power. We start with local affine features selected and n...
Andrea Vedaldi, Stefano Soatto
ISBI
2004
IEEE
15 years 10 months ago
Nonlinear Dimension Reduction of fMRI Data: The Laplacian Embedding Approach
In this paper, we introduce the use of nonlinear dimension reduction for the analysis of functional neuroimaging datasets. Using a Laplacian Embedding approach, we show the power ...
Olivier D. Faugeras, Bertrand Thirion
112
Voted
PAMI
2012
12 years 12 months ago
Trainable Convolution Filters and Their Application to Face Recognition
—In this paper, we present a novel image classification system that is built around a core of trainable filter ensembles that we call Volterra kernel classifiers. Our system trea...
Ritwik Kumar, Arunava Banerjee, Baba C. Vemuri, Ha...