725 search results - page 49 / 145 » Invariances in kernel methods: From samples to objects |
155
click to vote
ECCV
2004
Springer
15 years 8 months ago
2004
Springer
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
136
Voted
CVPR
2006
IEEE
16 years 5 months ago
2006
IEEE
We investigate the problem of learning the structure of an articulated object, i.e. its kinematic chain, from feature trajectories under affine projections. We demonstrate this po...
114
Voted
ISVC
2010
Springer
15 years 1 months ago
2010
Springer
SIFT is one of the most popular algorithms to extract points of interest from images. It is a scale+rotation invariant method. As a consequence, if one compares points of interest ...
132
click to vote
NIPS
2004
15 years 4 months ago
2004
Most existing tracking algorithms construct a representation of a target object prior to the tracking task starts, and utilize invariant features to handle appearance variation of...
173
click to vote
CVPR
2009
IEEE
16 years 10 months ago
2009
IEEE
Cross-domain learning methods have shown promising
results by leveraging labeled patterns from auxiliary domains
to learn a robust classifier for target domain, which
has a limi...