CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Multi-Instance Multi-Label Learning Combining Hierarchical Context and its Application to Image Annotation
Ding, Xinmiao1; Li, Bing2; Xiong, Weihua2; Guo, Wen1; Hu, Weiming3; Wang, Bo2
Source PublicationIEEE TRANSACTIONS ON MULTIMEDIA
2016-08-01
Volume18Issue:8Pages:1616-1627
SubtypeArticle
AbstractIn image annotation, one image is often modeled as a bag of regions ("instances") associated with multiple labels, which is a typical application of multi-instance multi-label learning (MIML). Although lots of research has shown that the interplay embedded among instances and labels can largely boost the image annotation accuracy, most existing MIML methods consider none or partial context cues. In this paper, we propose a novel context-aware MIML model to integrate the instance context and label context into a general framework. Specially, the instance context is constructed with multiple graphs, while the label context is built up through a linear combination of several common latent conceptions that link low level features and high level semantic labels. Comparison with other leading methods on several benchmark datasets in terms of image annotation shows that our proposed method can get better performance than the state-of-the-art approaches.
KeywordImage Annotation Instance Context Label Context Multi-instance Multi-label
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TMM.2016.2572000
WOS KeywordBI-RELATIONAL GRAPH ; CLASSIFICATION ; CATEGORIZATION ; SYSTEM
Indexed BySCI
Language英语
Funding Organization973 basic research program of China(2014CB349303) ; Natural Science Foundation of China(61472421 ; Strategic Priority Research Program of the CAS(XDB02070003) ; Natural Science Foundation of Shandong Province(ZR2015FL020) ; 61370038 ; 61303086 ; 61572296 ; 61503219 ; 61472227)
WOS Research AreaComputer Science ; Telecommunications
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS IDWOS:000379978000014
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12163
Collection模式识别国家重点实验室_视频内容安全
Affiliation1.Shandong Technol & Business Univ, Yantai 264005, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Inst Automat, CAS Ctr Excellence Brain Sci & Intelligence Techn, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Ding, Xinmiao,Li, Bing,Xiong, Weihua,et al. Multi-Instance Multi-Label Learning Combining Hierarchical Context and its Application to Image Annotation[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2016,18(8):1616-1627.
APA Ding, Xinmiao,Li, Bing,Xiong, Weihua,Guo, Wen,Hu, Weiming,&Wang, Bo.(2016).Multi-Instance Multi-Label Learning Combining Hierarchical Context and its Application to Image Annotation.IEEE TRANSACTIONS ON MULTIMEDIA,18(8),1616-1627.
MLA Ding, Xinmiao,et al."Multi-Instance Multi-Label Learning Combining Hierarchical Context and its Application to Image Annotation".IEEE TRANSACTIONS ON MULTIMEDIA 18.8(2016):1616-1627.
Files in This Item: Download All
File Name/Size DocType Version Access License
Multi-Instance Multi(549KB)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
[Ding, Xinmiao]'s Articles
[Li, Bing]'s Articles
[Xiong, Weihua]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ding, Xinmiao]'s Articles
[Li, Bing]'s Articles
[Xiong, Weihua]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ding, Xinmiao]'s Articles
[Li, Bing]'s Articles
[Xiong, Weihua]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Multi-Instance Multi-Label Learning Combining.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

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