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.
Content-based image retrieval, semantic-assisted visual hashing, auxiliary texts, unsupervised learning
Graphics and Human Computer Interfaces | Programming Languages and Compilers
IEEE Transactions on Knowledge and Data Engineering
Institute of Electrical and Electronics Engineers (IEEE)
ZHU, Lei; SHEN, Jialie; XIE, Liang; and CHENG, Zhiyong.
Unsupervised visual hashing with semantic assistant for content-based image retrieval. (2017). IEEE Transactions on Knowledge and Data Engineering. 29, (2), 472-486. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3811
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.