Sciweavers

3823 search results - page 500 / 765
» Experiments with Random Projection
Sort
View
CVPR
2009
IEEE
16 years 10 months ago
Active Learning for Large Multi-class Problems
Scarcity and infeasibility of human supervision for large scale multi-class classification problems necessitates active learning. Unfortunately, existing active learning methods ...
Prateek Jain (University of Texas at Austin), Ashi...
ICCV
2009
IEEE
3167views Computer Vision» more  ICCV 2009»
16 years 8 months ago
Tracking a Hand Manipulating an Object
We present a method for tracking a hand while it is interacting with an object. This setting is arguably the one where hand-tracking has most practical relevance, but poses signi...
Henning Hamer, Konrad Schindler, Esther Koller-Mei...
CVPR
1996
IEEE
16 years 5 months ago
MUSE: Robust Surface Fitting using Unbiased Scale Estimates
Despite many successful applications of robust statistics, they have yet to be completely adapted to many computer vision problems. Range reconstruction, particularly in unstructu...
James V. Miller, Charles V. Stewart
CVPR
2000
IEEE
16 years 5 months ago
Learning in Gibbsian Fields: How Accurate and How Fast Can It Be?
?Gibbsian fields or Markov random fields are widely used in Bayesian image analysis, but learning Gibbs models is computationally expensive. The computational complexity is pronoun...
Song Chun Zhu, Xiuwen Liu
CVPR
2003
IEEE
16 years 5 months ago
Object Recognition Based on Photometric Alignment Using RANSAC
For object recognition under varying illumination conditions, we propose a method based on photometric alignment. The photometric alignment is known as a technique that models bot...
Takahiro Okabe, Yoichi Sato