Sciweavers

313 search results - page 6 / 63
» Estimating labels from label proportions
Sort
View
ECCV
2010
Springer
15 years 3 months ago
Enhancing Interactive Image Segmentation with Automatic Label Set Augmentation
Abstract. We address the problem of having insufficient labels in an interactive image segmentation framework, for which most current methods would fail without further user inter...
ICML
2009
IEEE
15 years 4 months ago
Supervised learning from multiple experts: whom to trust when everyone lies a bit
We describe a probabilistic approach for supervised learning when we have multiple experts/annotators providing (possibly noisy) labels but no absolute gold standard. The proposed...
Vikas C. Raykar, Shipeng Yu, Linda H. Zhao, Anna K...
ICCV
2007
IEEE
15 years 11 months ago
Correspondence labelling for wide-timeframe free-form surface matching
This paper addresses the problem of estimating dense correspondence between arbitrary frames from captured sequences of shape and appearance for surfaces undergoing free-form defo...
Jonathan Starck, Adrian Hilton
ICASSP
2009
IEEE
15 years 4 months ago
Unsupervised acoustic and language model training with small amounts of labelled data
We measure the effects of a weak language model, estimated from as little as 100k words of text, on unsupervised acoustic model training and then explore the best method of using ...
Scott Novotney, Richard M. Schwartz, Jeff Ma
RSA
2010
64views more  RSA 2010»
14 years 8 months ago
Vertices of given degree in series-parallel graphs
We show that the number of vertices of a given degree k in several kinds of series-parallel labelled graphs of size n satisfy a central limit theorem with mean and variance proport...
Michael Drmota, Omer Giménez, Marc Noy