Sciweavers

313 search results - page 22 / 63
» Estimating labels from label proportions
Sort
View
IJCV
2011
152views more  IJCV 2011»
14 years 6 months ago
Recovering Occlusion Boundaries from an Image
Occlusion reasoning is a fundamental problem in computer vision. In this paper, we propose an algorithm to recover the occlusion boundaries and depth ordering of free-standing str...
Derek Hoiem, Alexei A. Efros, Martial Hebert
ICML
2005
IEEE
16 years 17 days ago
Beyond the point cloud: from transductive to semi-supervised learning
Due to its occurrence in engineering domains and implications for natural learning, the problem of utilizing unlabeled data is attracting increasing attention in machine learning....
Vikas Sindhwani, Partha Niyogi, Mikhail Belkin
VLSM
2005
Springer
15 years 5 months ago
Entropy Controlled Gauss-Markov Random Measure Field Models for Early Vision
We present a computationally efficient segmentationrestoration method, based on a probabilistic formulation, for the joint estimation of the label map (segmentation) and the para...
Mariano Rivera, Omar Ocegueda, José L. Marr...
NIPS
2007
15 years 1 months ago
Statistical Analysis of Semi-Supervised Regression
Semi-supervised methods use unlabeled data in addition to labeled data to construct predictors. While existing semi-supervised methods have shown some promising empirical performa...
John D. Lafferty, Larry A. Wasserman

Publication
279views
14 years 6 months ago
Colour Invariant Head Pose Classification in Low Resolution Video
This paper presents an algorithm for the classification of head pose in low resolution video. Invariance to skin, hair and background colours is achieved by classifying using an en...
Ben Benfold and Ian Reid