Publication Type

Journal Article

Version

acceptedVersion

Publication Date

8-2015

Abstract

This paper introduces a novel approach to facilitating image search based on a compact semantic embedding. A novel method is developed to explicitly map concepts and image contents into a unified latent semantic space for the representation of semantic concept prototypes. Then, a linear embedding matrix is learned that maps images into the semantic space, such that each image is closer to its relevant concept prototype than other prototypes. In our approach, the semantic concepts equated with query keywords and the images mapped into the vicinity of the prototype are retrieved by our scheme. In addition, a computationally efficient method is introduced to incorporate new semantic concept prototypes into the semantic space by updating the embedding matrix. This novelty improves the scalability of the method and allows it to be applied to dynamic image repositories. Therefore, the proposed approach not only narrows semantic gap but also supports an efficient image search process. We have carried out extensive experiments on various cross-modality image search tasks over three widely-used benchmark image datasets. Results demonstrate the superior effectiveness, efficiency, and scalability of our proposed approach.

Keywords

Compact semantic mapping (CSM), image search, semantic gap

Discipline

Computer Sciences | Databases and Information Systems

Publication

IEEE Transactions on Cybernetics

Volume

45

Issue

8

First Page

1561

Last Page

1574

ISBN

2168-2267

Identifier

10.1109/TCYB.2014.2356136

Publisher

IEEE

Comments

Formerly IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Additional URL

http://dx.doi.org/10.1109/TCYB.2014.2356136

Download

Share

COinS