Sciweavers

173 search results - page 5 / 35
» Structural Representations for Learning Relations between Pa...
Sort
View
CVPR
2007
IEEE
14 years 28 days ago
High Distortion and Non-Structural Image Matching via Feature Co-occurrence
We propose a novel approach for determining if a pair of images match each other under the effect of a highdistortion transformation or non-structural relation. The co-occurrence ...
Xi Chen, Tat-Jen Cham
CIKM
2008
Springer
13 years 8 months ago
Kernel methods, syntax and semantics for relational text categorization
Previous work on Natural Language Processing for Information Retrieval has shown the inadequateness of semantic and syntactic structures for both document retrieval and categoriza...
Alessandro Moschitti
ICML
2001
IEEE
14 years 7 months ago
Learning Probabilistic Models of Relational Structure
Most real-world data is stored in relational form. In contrast, most statistical learning methods work with "flat" data representations, forcing us to convert our data i...
Lise Getoor, Nir Friedman, Daphne Koller, Benjamin...
PAMI
2006
117views more  PAMI 2006»
13 years 6 months ago
Metric Learning for Text Documents
High dimensional structured data such as text and images is often poorly understood and misrepresented in statistical modeling. The standard histogram representation suffers from ...
Guy Lebanon
LREC
2008
193views Education» more  LREC 2008»
13 years 8 months ago
Eksairesis: A Domain-Adaptable System for Ontology Building from Unstructured Text
This paper describes Eksairesis, a system for learning economic domain knowledge automatically from Modern Greek text. The knowledge is in the form of economic terms and the seman...
Katia Kermanidis, Aristomenis Thanopoulos, Manolis...