Sciweavers

1463 search results - page 57 / 293
» Feature selection based on the training set manipulation
Sort
View
ICIP
2010
IEEE
13 years 5 months ago
Fast pedestrian detection with multi-scale orientation features and two-stage classifiers
In this paper, we propose an approach for fast pedestrian detection in images. Inspired by the histogram of oriented gradient (HOG) features, a set of multi-scale orientation (MSO...
Qixiang Ye, Jianbin Jiao, Baochang Zhang
COLING
2008
13 years 9 months ago
Authorship Attribution and Verification with Many Authors and Limited Data
Most studies in statistical or machine learning based authorship attribution focus on two or a few authors. This leads to an overestimation of the importance of the features extra...
Kim Luyckx, Walter Daelemans
ICPR
2002
IEEE
14 years 8 months ago
Narrative Structure Analysis with Education and Training Videos for E-Learning
This paper deals with the problem of structuralizing education and training videos for high-level semantics extraction and nonlinear media presentation in e-learning applications....
Quoc Dinh Phung, Chitra Dorai, Svetha Venkatesh
IJCNN
2006
IEEE
14 years 1 months ago
Training of Large-Scale Feed-Forward Neural Networks
Abstract— Neural processing of large-scale data sets containing both many input / output variables and a large number of training examples often leads to very large networks. Onc...
Udo Seiffert
ICPR
2004
IEEE
14 years 8 months ago
Enhancements for Local Feature Based Image Classification
Using local features with nearest neighbor search and direct voting obtains excellent results for various image classification tasks. In this work we decompose the method into its...
Daniel Keysers, Hermann Ney, Roberto Paredes, Tobi...