A Multimedia Semantic Retrieval Mobile System Based on HCFGs

Author

Yimin Yang ; Hsin-Yu Ha ; Fleites, Fausto C. ; Shu-Ching Chen

Volume

21

Issue

1

fYear

2014

fDate

Jan.-Mar. 2014

Firstpage

36

Lastpage

46

Abstract

A multimedia semantic retrieval system based on hidden coherent feature groups (HCFGs) can support multimedia semantic retrieval on mobile applications. The system can capture the correlation between features and partition the original feature set into HCFGs, which have strong intragroup correlation while maintaining low intercorrelation. The authors present a novel, multimodel fusion scheme to effectively fuse the multimodel results and generate the final ranked retrieval results. In addition, to incorporate user interaction for effective retrieval, the proposed system also features a user feedback mechanism that helps refine the retrieval results.

Keywords

group theory; information retrieval systems; mobile computing; multimedia systems; sensor fusion; HCFG; feature set partition; hidden coherent feature groups; intercorrelation; intragroup correlation; multimedia semantic retrieval mobile system; multimodel fusion scheme; retrieval results ranking; user feedback mechanism; user interaction; Feature extraction; Hidden Markov models; Information retrieval; Mobile communication; Mobile computing; Multimedia communication; Semantics; HCFGs; affinity propagation; correlation; hidden coherent feature groups; mobile applications; mobile computing; multimedia; multimedia data management; multimedia semantic retrieval; multimodel fusion;

fLanguage

English

Journal_Title

MultiMedia, IEEE

Publisher

ieee

ISSN

1070-986X

Type

jour

DOI

10.1109/MMUL.2013.33

Filename

6560008