2934 search results - page 474 / 587 » Hypothesis Spaces for Learning |
179
click to vote
CVPR
2008
IEEE
16 years 8 months ago
2008
IEEE
We propose a novel approach for activity analysis in multiple synchronized but uncalibrated static camera views. We assume that the topology of camera views is unknown and quite a...
145
click to vote
CVPR
2008
IEEE
16 years 8 months ago
2008
IEEE
Learning a discriminant becomes substantially more difficult when the datasets are high-dimensional and the available samples are few. This is often the case in computer vision an...
139
click to vote
CVPR
2008
IEEE
16 years 8 months ago
2008
IEEE
We present a method for learning discriminative linear feature extraction using independent tasks. More concretely, given a target classification task, we consider a complementary...
191
click to vote
ECCV
2008
Springer
16 years 8 months ago
2008
Springer
Viewpoint invariant pedestrian recognition is an important yet under-addressed problem in computer vision. This is likely due to the difficulty in matching two objects with unknown...
192
click to vote
ECCV
2006
Springer
16 years 8 months ago
2006
Springer
This paper presents a learning based approach to tracking articulated human body motion from a single camera. In order to address the problem of pose ambiguity, a one-to-many mappi...