Sciweavers

342 search results - page 57 / 69
» Learning from Ambiguously Labeled Images
Sort
View
CVPR
2012
IEEE
11 years 11 months ago
Learning 3D object templates by hierarchical quantization of geometry and appearance spaces
This paper presents a method for learning 3D object templates from view labeled object images. The 3D template is defined in a joint appearance and geometry space, and is compose...
Wenze Hu
EMMCVPR
2005
Springer
14 years 2 months ago
Exploiting Inference for Approximate Parameter Learning in Discriminative Fields: An Empirical Study
Abstract. Estimation of parameters of random field models from labeled training data is crucial for their good performance in many image analysis applications. In this paper, we p...
Sanjiv Kumar, Jonas August, Martial Hebert
FLAIRS
2004
13 years 9 months ago
A Faster Algorithm for Generalized Multiple-Instance Learning
In our prior work, we introduced a generalization of the multiple-instance learning (MIL) model in which a bag's label is not based on a single instance's proximity to a...
Qingping Tao, Stephen D. Scott
CVPR
2011
IEEE
13 years 4 months ago
Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds
Active learning and crowdsourcing are promising ways to efficiently build up training sets for object recognition, but thus far techniques are tested in artificially controlled ...
Sudheendra Vijayanarasimhan, Kristen Grauman
IPMI
2009
Springer
14 years 9 months ago
Fully-Automated White Matter Hyperintensity Detection With Anatomical Prior Knowledge and Without FLAIR
This paper presents a method for detection of cerebral white matter hyperintensities (WMH) based on run-time PD-, T1-, and T2weighted structural magnetic resonance (MR) images of t...
Charles DeCarli, Christopher Schwarz, Evan Fletche...