183
click to vote
ICCV
2007
IEEE
16 years 5 months ago
2007
IEEE
In this paper, we propose a novel metric learning method based on regularized moving least squares. Unlike most previous metric learning methods which learn a global Mahalanobis d...
ICCV
2007
IEEE
16 years 5 months ago
2007
IEEE
137
click to vote
ICCV
2007
IEEE
16 years 5 months ago
2007
IEEE
The k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on ...
225
click to vote
ICCV
2007
IEEE
16 years 5 months ago
2007
IEEE
In this paper we propose a method for matching articulated shapes represented as large sets of 3D points by aligning the corresponding embedded clouds generated by locally linear ...
172
click to vote
ICCV
2007
IEEE
16 years 5 months ago
2007
IEEE
This paper presents a method for scene flow estimation from a calibrated stereo image sequence. The scene flow contains the 3-D displacement field of scene points, so that the 2-D...