Sciweavers

1859 search results - page 223 / 372
» Using Problems to Learn Service-Oriented Computing
Sort
View
168
Voted
IJCAI
2007
15 years 6 months ago
Kernel Conjugate Gradient for Fast Kernel Machines
We propose a novel variant of the conjugate gradient algorithm, Kernel Conjugate Gradient (KCG), designed to speed up learning for kernel machines with differentiable loss functio...
Nathan D. Ratliff, J. Andrew Bagnell
MVA
2010
181views Computer Vision» more  MVA 2010»
15 years 3 months ago
Human action detection via boosted local motion histograms
This paper presents a novel learning method for human action detection in video sequences. The detecting problem is not limited in controlled settings like stationary background or...
Qingshan Luo, Xiaodong Kong, Guihua Zeng, Jianping...
ICPR
2008
IEEE
16 years 6 months ago
Recognition of books by verification and retraining
The problem of character recognition in a book should be formulated significantly different from that of a single page or word. An ideal approach to design such a recognizer is to...
C. V. Jawahar, N. V. Neeba
ICPR
2008
IEEE
16 years 6 months ago
Texture classification with minimal training images
The objective of this work is classifying texture from a single image under unknown lighting conditions. The current and successful approach to this task is to treat it as a stati...
Alireza Tavakoli Targhi, Jan-Mark Geusebroek, Andr...
ICML
2007
IEEE
16 years 5 months ago
Best of both: a hybridized centroid-medoid clustering heuristic
Although each iteration of the popular kMeans clustering heuristic scales well to larger problem sizes, it often requires an unacceptably-high number of iterations to converge to ...
Nizar Grira, Michael E. Houle