Learning semantic concepts from user feedback log for image retrieval

Junwei Han, King N. Ngan, Mingjing Li, Hongjiang Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

To improve the performance of image retrieval systems, the well-known semantic gap needs to be bridged. Relevance feedback provides a strategy for learning semantic concepts from visual features. This paper reports a novel framework to learn semantic concepts from accumulated user feedback log. The semantic concepts consist of two categories: explicit semantics and implicit semantics. The former can be directly estimated by analyzing user-provided feedback log. The latter is learned according to the obtained explicit semantics. Finally, both explicit and implicit semantics are applied to an image retrieval system. Experiments on 10,000 images show the superiority of the proposed method.

Original languageEnglish
Title of host publication2004 IEEE International Conference on Multimedia and Expo (ICME)
Pages995-998
Number of pages4
StatePublished - 2004
Externally publishedYes
Event2004 IEEE International Conference on Multimedia and Expo (ICME) - Taipei, Taiwan, Province of China
Duration: 27 Jun 200430 Jun 2004

Publication series

Name2004 IEEE International Conference on Multimedia and Expo (ICME)
Volume2

Conference

Conference2004 IEEE International Conference on Multimedia and Expo (ICME)
Country/TerritoryTaiwan, Province of China
CityTaipei
Period27/06/0430/06/04

Fingerprint

Dive into the research topics of 'Learning semantic concepts from user feedback log for image retrieval'. Together they form a unique fingerprint.

Cite this