Sciweavers

4639 search results - page 28 / 928
» A General Method for Errors-in-Variables Problems in Compute...
Sort
View
CVPR
2012
IEEE
11 years 11 months ago
Mode-seeking on graphs via random walks
Mode-seeking has been widely used as a powerful data analysis technique for clustering and filtering in a metric feature space. We introduce a versatile and efficient modeseekin...
Minsu Cho, Kyoung Mu Lee
MVA
1992
188views Computer Vision» more  MVA 1992»
13 years 9 months ago
The Programmable and Configurable Low Level Vision Unit of the HERMIA Machine
In this work the Low Level Vision Unit (LLVU) of the Heterogeneous and Reconfigurable Machine for Image Analysis (HERMIA) is described. The LLVU consists of the innovative integra...
Gaetano Gerardi, Giancarlo Parodi
CVPR
2012
IEEE
11 years 11 months ago
General trajectory prior for Non-Rigid reconstruction
Trajectory basis Non-Rigid Structure From Motion (NRSFM) currently faces two problems: the limit of reconstructability and the need to tune the basis size for different sequences....
Jack Valmadre, Simon Lucey
3DPVT
2006
IEEE
213views Visualization» more  3DPVT 2006»
14 years 2 months ago
Generalized RANSAC Framework for Relaxed Correspondence Problems
Finding correspondences between two (widely) separated views is essential for several computer vision tasks, such as structure and motion estimation and object recognition. In the...
Wei Zhang, Jana Kosecka
ICPR
2010
IEEE
13 years 10 months ago
SemiCCA: Efficient Semi-Supervised Learning of Canonical Correlations
Canonical correlation analysis (CCA) is a powerful tool for analyzing multi-dimensional paired data. However, CCA tends to perform poorly when the number of paired samples is limit...
Akisato Kimura, Hirokazu Kameoka, Masashi Sugiyama...