Unsupervised visual hashing with semantic assistant for content-based image retrieval
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). Distingui...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2017
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/3811 https://ink.library.smu.edu.sg/context/sis_research/article/4813/viewcontent/07464865__1_.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-4813 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-48132018-09-13T08:17:21Z Unsupervised visual hashing with semantic assistant for content-based image retrieval ZHU, Lei SHEN, Jialie XIE, Liang CHENG, Zhiyong 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. 2017-02-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/3811 info:doi/10.1109/TKDE.2016.2562624 https://ink.library.smu.edu.sg/context/sis_research/article/4813/viewcontent/07464865__1_.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Content-based image retrieval semantic-assisted visual hashing auxiliary texts unsupervised learning Databases and Information Systems Graphics and Human Computer Interfaces |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Content-based image retrieval semantic-assisted visual hashing auxiliary texts unsupervised learning Databases and Information Systems Graphics and Human Computer Interfaces |
spellingShingle |
Content-based image retrieval semantic-assisted visual hashing auxiliary texts unsupervised learning Databases and Information Systems Graphics and Human Computer Interfaces ZHU, Lei SHEN, Jialie XIE, Liang CHENG, Zhiyong Unsupervised visual hashing with semantic assistant for content-based image retrieval |
description |
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. |
format |
text |
author |
ZHU, Lei SHEN, Jialie XIE, Liang CHENG, Zhiyong |
author_facet |
ZHU, Lei SHEN, Jialie XIE, Liang CHENG, Zhiyong |
author_sort |
ZHU, Lei |
title |
Unsupervised visual hashing with semantic assistant for content-based image retrieval |
title_short |
Unsupervised visual hashing with semantic assistant for content-based image retrieval |
title_full |
Unsupervised visual hashing with semantic assistant for content-based image retrieval |
title_fullStr |
Unsupervised visual hashing with semantic assistant for content-based image retrieval |
title_full_unstemmed |
Unsupervised visual hashing with semantic assistant for content-based image retrieval |
title_sort |
unsupervised visual hashing with semantic assistant for content-based image retrieval |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2017 |
url |
https://ink.library.smu.edu.sg/sis_research/3811 https://ink.library.smu.edu.sg/context/sis_research/article/4813/viewcontent/07464865__1_.pdf |
_version_ |
1770573766937542656 |