Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Social Image Tag Recommendation by Concept Matching axsun@ntu.edu.sg
 

Summary: Social Image Tag Recommendation by Concept Matching
Aixin Sun
axsun@ntu.edu.sg
Sourav S. Bhowmick
assourav@ntu.edu.sg
Jun-An Chong
chon0113@e.ntu.edu.sg
School of Computer Engineering, Nanyang Technological University, Singapore 639798
ABSTRACT
Tags associated with social images are valuable information source
for superior image search and retrieval experiences. In this paper,
we propose a novel tag recommendation technique that exploits
the user-given tags associated with images. Each candidate tag to
be recommended is described by a few tag concepts derived from
the collective knowledge embedded in the tag co-occurrence pairs.
Each concept, represented by a few tags with high co-occurrences
among themselves, is indexed as a textual document. Then user-
given tags of an image is represented as a text query and the match-
ing concepts are retrieved from the index. The candidate tags asso-
ciated with the matching concepts are then recommended. Lever-

  

Source: Aixin, Sun - School of Computer Engineering, Nanyang Technological University

 

Collections: Computer Technologies and Information Sciences