Issue No. 01 - Jan.-Mar. (2014 vol. 21)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MMUL.2013.33
Yimin Yang , Florida International University
Hsin-Yu Ha , Florida International University
Fausto C. Fleites , Florida International University
Shu-Ching Chen , Florida International University
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.
Information retrieval, Multimedia communication, Feature extraction, Semantics, Hidden Markov models, Mobile computing, Mobile communication
Y. Yang, H. Ha, F. C. Fleites and S. Chen, "A Multimedia Semantic Retrieval Mobile System Based on HCFGs," in IEEE MultiMedia, vol. 21, no. 1, pp. 36-46, 2014.