Sciweavers

365 search results - page 31 / 73
» Visual Tracking Using Learned Linear Subspaces
Sort
View
114
Voted
ICML
2007
IEEE
16 years 1 months ago
Classifying matrices with a spectral regularization
We propose a method for the classification of matrices. We use a linear classifier with a novel regularization scheme based on the spectral 1-norm of its coefficient matrix. The s...
Ryota Tomioka, Kazuyuki Aihara
89
Voted
CVPR
2008
IEEE
16 years 2 months ago
Learning and using taxonomies for fast visual categorization
The computational complexity of current visual categorization algorithms scales linearly at best with the number of categories. The goal of classifying simultaneously Ncat = 104 -...
Gregory Griffin, Darya Perona
118
Voted
AUSAI
2004
Springer
15 years 5 months ago
Enhanced Importance Sampling: Unscented Auxiliary Particle Filtering for Visual Tracking
Abstract. The particle filter has attracted considerable attention in visual tracking due to its relaxation of the linear and Gaussian restrictions in the state space model. It is...
Chunhua Shen, Anton van den Hengel, Anthony R. Dic...
CORR
2010
Springer
204views Education» more  CORR 2010»
14 years 11 months ago
Predictive State Temporal Difference Learning
We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with subspace identification. In practical applications...
Byron Boots, Geoffrey J. Gordon
98
Voted
FGR
1996
IEEE
117views Biometrics» more  FGR 1996»
15 years 4 months ago
Tracking and Learning Graphs and Pose on Image Sequences of Faces
We demonstrate a system capable of tracking, in real world image sequences, landmarks such as eyes, mouth, or chin on a face. In the standard version, knowledge previously collect...
Thomas Maurer, Christoph von der Malsburg