Sciweavers

43 search results - page 2 / 9
» Evaluating Classifiers by Means of Test Data with Noisy Labe...
Sort
View
AIPRF
2007
13 years 6 months ago
Evaluation of Different Approaches to Training a Genre Classifier
This paper presents experiments on classifying web pages by genre. Firstly, a corpus of 1539 manually labeled web pages was prepared. Secondly, 502 genre features were selected ba...
Vedrana Vidulin, Mitja Lustrek, Matjaz Gams
PKDD
2010
Springer
128views Data Mining» more  PKDD 2010»
13 years 3 months ago
Learning to Tag from Open Vocabulary Labels
Most approaches to classifying media content assume a fixed, closed vocabulary of labels. In contrast, we advocate machine learning approaches which take advantage of the millions...
Edith Law, Burr Settles, Tom M. Mitchell
KDD
2003
ACM
157views Data Mining» more  KDD 2003»
14 years 5 months ago
Cross-training: learning probabilistic mappings between topics
Classification is a well-established operation in text mining. Given a set of labels A and a set DA of training documents tagged with these labels, a classifier learns to assign l...
Sunita Sarawagi, Soumen Chakrabarti, Shantanu Godb...
MCS
2005
Springer
13 years 10 months ago
Mixture of Gaussian Processes for Combining Multiple Modalities
This paper describes a unified approach, based on Gaussian Processes, for achieving sensor fusion under the problematic conditions of missing channels and noisy labels. Under the ...
Ashish Kapoor, Hyungil Ahn, Rosalind W. Picard
ICPR
2004
IEEE
14 years 6 months ago
Conformal Method for Quantitative Shape Extraction: Performance Evaluation
We evaluate our recently developed conformal method for quantitative shape extraction from unorganized 3D oriented point clouds. The conformal method has been tested previously on...
George Kamberov, Gerda Kamberova