Sciweavers

39 search results - page 4 / 8
» Feature Extraction base on Local Maximum Margin Criterion
Sort
View
TNN
2010
234views Management» more  TNN 2010»
13 years 2 months ago
Novel maximum-margin training algorithms for supervised neural networks
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Oswaldo Ludwig, Urbano Nunes
CVPR
1997
IEEE
14 years 6 days ago
Normalized Cuts and Image Segmentation
ÐWe propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach ...
Jianbo Shi, Jitendra Malik
FGR
2008
IEEE
208views Biometrics» more  FGR 2008»
14 years 2 months ago
Unsupervised learning from local features for video-based face recognition
This paper presents an unsupervised learning approach to video-based face recognition that does not make any assumptions about the pose, expressions or prior localization of landm...
Ajmal Mian
FGR
2011
IEEE
268views Biometrics» more  FGR 2011»
12 years 11 months ago
Emotion recognition using PHOG and LPQ features
— We propose a method for automatic emotion recognition as part of the FERA 2011 competition [1] . The system extracts pyramid of histogram of gradients (PHOG) and local phase qu...
Abhinav Dhall, Akshay Asthana, Roland Goecke, Tom ...
ICASSP
2010
IEEE
13 years 8 months ago
Summarization- and learning-based approaches to information distillation
Information distillation is the task that aims to extract relevant passages of text from massive volumes of textual and audio sources, given a query. In this paper, we investigate...
Boriska Toth, Dilek Hakkani-Tür, Sibel Yaman