Sciweavers

603 search results - page 48 / 121
» A discriminative model for semi-supervised learning
Sort
View
ICPR
2010
IEEE
14 years 2 days ago
Efficient Learning to Label Images
Conditional random field methods (CRFs) have gained popularity for image labeling tasks in recent years. In this paper, we describe an alternative discriminative approach, by exte...
Ke Jia, Li Cheng, Nianjun Liu, Lei Wang
CVPR
2007
IEEE
14 years 10 months ago
Transfer Learning in Sign language
We build word models for American Sign Language (ASL) that transfer between different signers and different aspects. This is advantageous because one could use large amounts of la...
Ali Farhadi, David A. Forsyth, Ryan White
TCSV
2008
195views more  TCSV 2008»
13 years 8 months ago
Locality Versus Globality: Query-Driven Localized Linear Models for Facial Image Computing
Conventional subspace learning or recent feature extraction methods consider globality as the key criterion to design discriminative algorithms for image classification. We demonst...
Yun Fu, Zhu Li, Junsong Yuan, Ying Wu, Thomas S. H...
NAACL
2010
13 years 6 months ago
Painless Unsupervised Learning with Features
We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. In particular, each component mul...
Taylor Berg-Kirkpatrick, Alexandre Bouchard-C&ocir...
ISWC
2006
IEEE
14 years 2 months ago
Towards Less Supervision in Activity Recognition from Wearable Sensors
Activity Recognition has gained a lot of interest in recent years due to its potential and usefulness for context-aware wearable computing. However, most approaches for activity r...
Tâm Huynh, Bernt Schiele