Sciweavers

2960 search results - page 124 / 592
» Learning from Multiple Sources
Sort
View
MMM
2008
Springer
119views Multimedia» more  MMM 2008»
15 years 4 months ago
Detecting and Clustering Multiple Takes of One Scene
Abstract. In applications such as video post-production users are confronted with large amounts of redundant unedited raw material, called rushes. Viewing and organizing this mater...
Werner Bailer, Felix Lee, Georg Thallinger
DCC
2007
IEEE
15 years 9 months ago
Multiple-Description Coding by Dithered Delta-Sigma Quantization
We address the connection between the multiple-description (MD) problem and Delta-Sigma quantization. The inherent redundancy due to oversampling in Delta-Sigma quantization, and ...
Jan Østergaard, Ram Zamir
ICML
2010
IEEE
14 years 11 months ago
OTL: A Framework of Online Transfer Learning
In this paper, we investigate a new machine learning framework called Online Transfer Learning (OTL) that aims to transfer knowledge from some source domain to an online learning ...
Peilin Zhao, Steven C. H. Hoi
ACL
2010
14 years 8 months ago
Bootstrapping Semantic Analyzers from Non-Contradictory Texts
We argue that groups of unannotated texts with overlapping and non-contradictory semantics represent a valuable source of information for learning semantic representations. A simp...
Ivan Titov, Mikhail Kozhevnikov
ICCV
2007
IEEE
15 years 4 months ago
Action Recognition from Arbitrary Views using 3D Exemplars
In this paper, we address the problem of learning compact, view-independent, realistic 3D models of human actions recorded with multiple cameras, for the purpose of recognizing th...
Daniel Weinland, Edmond Boyer, Rémi Ronfard