5305 search results - page 834 / 1061 » Modeling Foveal Vision |
159
click to vote
CVPR
2010
IEEE
16 years 3 months ago
2010
IEEE
Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of interme...
207
click to vote
CVPR
2010
IEEE
16 years 3 months ago
2010
IEEE
Markerless tracking of human pose is a hard yet relevant problem. In this paper, we derive an efficient filtering algorithm for tracking human pose at 4-10 frames per second using...
165
click to vote
CVPR
2010
IEEE
16 years 2 months ago
2010
IEEE
Psychologists have proposed that many human-object interaction activities form unique classes of scenes. Recognizing these scenes is important for many social functions. To enable...
189
click to vote
CVPR
2010
IEEE
16 years 2 months ago
2010
IEEE
How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without huma...
168
click to vote
CVPR
2010
IEEE
16 years 2 months ago
2010
IEEE
A central problem in the analysis of motion capture (Mo-
Cap) data is how to decompose motion sequences into primitives.
Ideally, a description in terms of primitives should
fac...