Sciweavers

38 search results - page 4 / 8
» Two-Step Classification Based on Scale Space
Sort
View
ACL
2010
13 years 5 months ago
Towards Open-Domain Semantic Role Labeling
Current Semantic Role Labeling technologies are based on inductive algorithms trained over large scale repositories of annotated examples. Frame-based systems currently make use o...
Danilo Croce, Cristina Giannone, Paolo Annesi, Rob...
SDM
2008
SIAM
140views Data Mining» more  SDM 2008»
13 years 9 months ago
Large-Scale Many-Class Learning
In many multiclass learning scenarios, the number of classes is relatively large (thousands,...), or the space and time efficiency of the learning system can be crucial. We invest...
Omid Madani, Michael Connor
ICPR
2008
IEEE
14 years 2 months ago
Figure-ground discrimination and distortion-tolerant recognition of color characters in scene images
This paper proposes a new technique of figureground discrimination of color characters in scene images following two steps. The first step is temporary binarization by selecting o...
Toru Wakahara
CN
2004
256views more  CN 2004»
13 years 7 months ago
A line in the sand: a wireless sensor network for target detection, classification, and tracking
Intrusion detection is a surveillance problem of practical import that is well suited to wireless sensor networks. In this paper, we study the application of sensor networks to the...
Anish Arora, Prabal Dutta, Sandip Bapat, Vinod Kul...
AAAI
2006
13 years 9 months ago
A Direct Evolutionary Feature Extraction Algorithm for Classifying High Dimensional Data
Among various feature extraction algorithms, those based on genetic algorithms are promising owing to their potential parallelizability and possible applications in large scale an...
Qijun Zhao, David Zhang, Hongtao Lu