CASIA OpenIR  > 精密感知与控制研究中心  > 人工智能与机器学习
Image automatic annotation via multi-view deep representation
Yang Y(杨阳); Zhang Wensheng(张文生); Xie Yuan; wensheng zhang
Source PublicationJournal of Visual Communication and Image Representation
2015
Volume2015Issue:33Pages:368-377
Abstract
The performance of text-based image retrieval is highly dependent on the tedious and inefficient manual work. For the purpose of realizing image keywords generated automatically, extensive work has been done in the area of image annotation. However, how to treat image diverse keywords and choose appropriate features are still two difficult problems. To address this challenge, we propose the multi-view stacked auto-encoder (MVSAE) framework to establish the correlations between the low-level visual features and high-level semantic information. In this paper, a new method, which incorporates the keyword frequencies and log-entropy, is presented to address the imbalanced distribution of keywords. In order to utilize the complementarities among diverse visual descriptors, we tactfully apply multi-view learning to
search for the label-specific features. Thereafter, the image keywords are finally produced by appropriate features. Conducting extensive experiments on three popular data sets, we demonstrate that our proposed framework can achieve effective and favorable performance for image annotation.
KeywordImage Annotation Stacked Auto-encoder Imbalance Learning Multi-view Learning Image Features Semantic Gap Deep Learning Multi-labeling
Indexed BySCI
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12090
Collection精密感知与控制研究中心_人工智能与机器学习
Corresponding Authorwensheng zhang
AffiliationInstitute of Automation, University of Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Yang Y,Zhang Wensheng,Xie Yuan,et al. Image automatic annotation via multi-view deep representation[J]. Journal of Visual Communication and Image Representation,2015,2015(33):368-377.
APA Yang Y,Zhang Wensheng,Xie Yuan,&wensheng zhang.(2015).Image automatic annotation via multi-view deep representation.Journal of Visual Communication and Image Representation,2015(33),368-377.
MLA Yang Y,et al."Image automatic annotation via multi-view deep representation".Journal of Visual Communication and Image Representation 2015.33(2015):368-377.
Files in This Item: Download All
File Name/Size DocType Version Access License
Image automatic anno(1988KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang Y(杨阳)]'s Articles
[Zhang Wensheng(张文生)]'s Articles
[Xie Yuan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang Y(杨阳)]'s Articles
[Zhang Wensheng(张文生)]'s Articles
[Xie Yuan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang Y(杨阳)]'s Articles
[Zhang Wensheng(张文生)]'s Articles
[Xie Yuan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Image automatic annotation via multi-view deep representation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.