342 search results - page 31 / 69 » Learning from Ambiguously Labeled Images |
BMVC
2010
13 years 6 months ago
2010
Gaussian processes have been widely used as a method for inferring the pose of articulated bodies directly from image data. While able to model complex non-linear functions, they ...
MICCAI
2009
Springer
14 years 9 months ago
2009
Springer
Segmentation of medical images is commonly formulated as a supervised learning problem, where manually labeled training data are summarized using a parametric atlas. Summarizing th...
CLEF
2010
Springer
13 years 9 months ago
2010
Springer
Abstract. This paper describes a visual localization approach for mobile robots. Robot localization is performed as location recognition. The approach uses global visual features (...
CVPR
2010
IEEE
14 years 4 months ago
2010
IEEE
In this paper, we deal with a generative model for multi-label, interactive segmentation. To estimate the pixel likelihoods for each label, we propose a new higher-order formulatio...
CVPR
2006
IEEE
14 years 10 months ago
2006
IEEE
We consider the general problem of learning from both labeled and unlabeled data. Given a set of data points, only a few of them are labeled, and the remaining points are unlabele...