Sciweavers

314 search results - page 9 / 63
» Using feature construction to avoid large feature spaces in ...
Sort
View
KDD
2010
ACM
197views Data Mining» more  KDD 2010»
13 years 5 months ago
Semi-supervised feature selection for graph classification
The problem of graph classification has attracted great interest in the last decade. Current research on graph classification assumes the existence of large amounts of labeled tra...
Xiangnan Kong, Philip S. Yu
ICDAR
2009
IEEE
14 years 2 months ago
Text Detection and Localization in Complex Scene Images using Constrained AdaBoost Algorithm
We have proposed a complete system for text detection and localization in gray scale scene images. A boosting framework integrating feature and weak classifier selection based on...
Shehzad Muhammad Hanif, Lionel Prevost
CVPR
2010
IEEE
14 years 1 days ago
Local Features Are Not Lonely - Laplacian Sparse Coding for Image Classification
Sparse coding which encodes the original signal in a sparse signal space, has shown its state-of-the-art performance in the visual codebook generation and feature quantization pro...
Shenghua Gao, Wai-Hung Tsang, Liang-Tien Chia, Pei...
ICIP
2005
IEEE
14 years 9 months ago
Using visual features for anti-spam filtering
Unsolicited Commercial Email (UCE), also known as spam, has been a major problem on the Internet. In the past, researchers have addressed this problem as a text classification or ...
Ching-Tung Wu, Kwang-Ting Cheng, Qiang Zhu, Yi-Leh...
KDD
2002
ACM
179views Data Mining» more  KDD 2002»
14 years 8 months ago
Combining clustering and co-training to enhance text classification using unlabelled data
In this paper, we present a new co-training strategy that makes use of unlabelled data. It trains two predictors in parallel, with each predictor labelling the unlabelled data for...
Bhavani Raskutti, Herman L. Ferrá, Adam Kow...