484 search results - page 34 / 97 » cvpr 2007 |
86
Voted
CVPR
2007
IEEE
16 years 8 days ago
2007
IEEE
Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...
92
Voted
CVPR
2007
IEEE
16 years 8 days ago
2007
IEEE
Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
75
Voted
CVPR
2007
IEEE
16 years 8 days ago
2007
IEEE
In patch-based object recognition, there are two important issues on the codebook generation: (1) resolution: a coarse codebook lacks sufficient discriminative power, and an over-...
91
Voted
CVPR
2007
IEEE
15 years 4 months ago
2007
IEEE
3D human pose recovery is considered as a fundamental step in view-invariant human action recognition. However, inferring 3D poses from a single view usually is slow due to the la...
CVPR
2007
IEEE
15 years 4 months ago
2007
IEEE
We propose a framework for general multiple target tracking, where the input is a set of candidate regions in each frame, as obtained from a state of the art background learning, ...