Publication Type

Journal Article

Publication Date

2-2017

Abstract

As an emerging technology to support scalable content-based image retrieval (CBIR), hashing has recently received great attention and became a very active research domain. In this study, we propose a novel unsupervised visual hashing approach called semantic-assisted visual hashing (SAVH). Distinguished from semi-supervised and supervised visual hashing, its core idea is to effectively extract the rich semantics latently embedded in auxiliary texts of images to boost the effectiveness of visual hashing without any explicit semantic labels. To achieve the target, a unified unsupervised framework is developed to learn hash codes by simultaneously preserving visual similarities of images, integrating the semantic assistance from auxiliary texts on modeling high-order relationships of inter-images, and characterizing the correlations between images and shared topics. Our performance study on three publicly available image collections: Wiki, MIR Flickr, and NUS-WIDE indicates that SAVH can achieve superior performance over several state-of-the-art techniques.

Keywords

Content-based image retrieval, semantic-assisted visual hashing, auxiliary texts, unsupervised learning

Discipline

Graphics and Human Computer Interfaces | Programming Languages and Compilers

Publication

IEEE Transactions on Knowledge and Data Engineering

Volume

29

Issue

2

First Page

472

Last Page

486

ISSN

1041-4347

Identifier

10.1109/TKDE.2016.2562624

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Additional URL

http://doi.org/10.1109/TKDE.2016.2562624

Share

COinS