Sciweavers

725 search results - page 58 / 145
» Invariances in kernel methods: From samples to objects
Sort
View
PROCEDIA
2010
119views more  PROCEDIA 2010»
13 years 7 months ago
Performance and accuracy of Lattice-Boltzmann kernels on multi- and manycore architectures
We present different kernels based on Lattice-Boltzmann methods for the solution of the twodimensional Shallow Water and Navier-Stokes equations on fully structured lattices. The...
Dirk Ribbrock, Markus Geveler, Dominik Göddek...
ECCV
2004
Springer
14 years 11 months ago
Adaptive Probabilistic Visual Tracking with Incremental Subspace Update
Visual tracking, in essence, deals with non-stationary data streams that change over time. While most existing algorithms are able to track objects well in controlled environments,...
David A. Ross, Jongwoo Lim, Ming-Hsuan Yang
CGF
2004
93views more  CGF 2004»
13 years 9 months ago
Prototype Modeling from Sketched Silhouettes based on Convolution Surfaces
This paper presents a hybrid method for creating three-dimensional shapes by sketching silhouette curves. Given a silhouette curve, we approximate its medial axis as a set of line...
Chiew-Lan Tai, Hongxin Zhang, Jacky Chun-Kin Fong
CIVR
2007
Springer
195views Image Analysis» more  CIVR 2007»
14 years 3 months ago
Towards optimal bag-of-features for object categorization and semantic video retrieval
Bag-of-features (BoF) deriving from local keypoints has recently appeared promising for object and scene classification. Whether BoF can naturally survive the challenges such as ...
Yu-Gang Jiang, Chong-Wah Ngo, Jun Yang 0003
CVPR
2010
IEEE
14 years 5 months ago
Comparative object similarity for improved recognition with few or no examples
Learning models for recognizing objects with few or no training examples is important, due to the intrinsic longtailed distribution of objects in the real world. In this paper, we...
Gang Wang, David Forsyth, Derek Hoiem