Novel Fusion Methods for Pattern Recognition thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Novel Fusion Methods for Pattern Recognition

Published on Nov 30, 20113239 Views

e last few years, several approaches have been proposed for information fusion including different variants of classifier level fusion (ensemble methods), stacking and multiple kernel learning (MKL).

Related categories

Chapter list

Novel Fusion Methods for Pattern Recognition00:00
Motivation00:16
Problem Statement00:43
Contents01:02
Multiple Kernel Learning (MKL)01:32
Classifier Level Fusion (CLF) - 102:20
Classifier Level Fusion (CLF) - 203:08
Classifier Level Fusion (CLF) - 303:42
Binary CLF with Non-Linear Constraints05:16
Multiclass CLF (NLP-νMC)06:25
Multiclass CLF (NLP-β)07:45
Multiclass CLF (NLP-B)08:49
Extended Stacking09:27
Base plus Stacking Kernel10:53
Results11:19
PASCAL VOC 2007 - 112:20
PASCAL VOC 2007 - 213:08
Results - 214:45
Mean Accuracy on Oxford Flower1715:28
Summary of Mean Accuracy on Computer Vision Datasets20:03
Protein Subcellular Localization20:11
Conclusions21:00
Thanks!22:54