Abstract
Learning ranking scores is critical for the multimedia database retrieval problem. In this paper, we propose a novel ranking score learning algorithm by exploring the sparse structure and using it to regularize ranking scores. To explore the sparse structure, we assume that each multimedia object could be represented as a sparse linear combination of all other objects, and combination coefficients are regarded as a similarity measure between objects and used to regularize their ranking scores. Moreover, we propose to learn the sparse combination coefficients and the ranking scores simultaneously. A unified objective function is constructed with regard to both the combination coefficients and the ranking scores, and is optimized by an iterative algorithm. Experiments on two multimedia database retrieval data sets demonstrate the significant improvements of the propose algorithm over state-of-the-art ranking score learning algorithms.
Original language | English (US) |
---|---|
Pages (from-to) | 635-654 |
Number of pages | 20 |
Journal | Multimedia Tools and Applications |
Volume | 74 |
Issue number | 2 |
DOIs | |
State | Published - Apr 17 2014 |
Bibliographical note
KAUST Repository Item: Exported on 2020-10-01Acknowledgements: Jim Jing-Yan Wang and Yijun Sun are in part supported by US National Science Foundation under grant No. DBI-1062362. The study is supported by grants from Provincial Key Laboratory for Computer Information Processing Technology, Soochow University, China, and King Abdullah University of Science and Technology (KAUST), Saudi Arabia.
ASJC Scopus subject areas
- Hardware and Architecture
- Media Technology
- Software
- Computer Networks and Communications