142 search results - page 20 / 29 » Segmenting Images on the Tensor Manifold |
NIPS
2004
15 years 1 months ago
2004
Many machine learning algorithms for clustering or dimensionality reduction take as input a cloud of points in Euclidean space, and construct a graph with the input data points as...
114
click to vote
ICIP
2005
IEEE
15 years 5 months ago
2005
IEEE
Averaging, filtering and interpolation of 3-D object orientation data is important in both computer vision and computer graphics, for instance to smooth estimates of object orien...
147
click to vote
VLSISP
2010
14 years 10 months ago
2010
Abstract In case of insufficient data samples in highdimensional classification problems, sparse scatters of samples tend to have many ‘holes’—regions that have few or no nea...
ICPR
2006
IEEE
16 years 23 days ago
2006
IEEE
This paper describes a new motion based feature extraction technique for speaker identification using orientation estimation in 2D manifolds. The motion is estimated by computing ...
105
click to vote
CVPR
2008
IEEE
16 years 1 months ago
2008
IEEE
Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...