Image Annotation Refinement using NSC-Based Word Correlation
Jing Liu; Mingjing Li; Qingshan Liu; Hanqing Lu; Songde Ma
2007
会议名称IEEE International Conference on Multimedia and Expo
会议录名称Proceedings of the 2007 IEEE International Conference on Multimedia and Expo
会议日期July 2-5, 2007
会议地点Beijing, China
摘要Image annotation refinement is crucial to improve the performance of automatic image annotation, in which the estimation of word correlation is a key issue. Typically, the word co-occurrence information may be utilized to estimate the word correlation. However, this approach is not accurate enough because it equally treats any word pair co-occurring in the training data and cannot extract synonymy relationship effectively. In this paper, a novel method is developed to estimate the word correlation based on the improved nearest spanning chains (NSC). It can extract more informative and reasonable relations among keywords. Obtaining the enhanced word correlation, a word-based graph is constructed, which is used to re-rank the candidate annotations for an untagged image. Experiments conducted on the typical Corel dataset demonstrate the effectiveness of the proposed method.
关键词Internet Graph Theory Image Retrieval Corel Dataset Nsc-based Word Correlation Automatic Image Annotation Candidate Annotations Image Annotation Refinement Nearest Spanning Chains Synonymy Relationship Untagged Image Word Co-occurrence Information Word Correlation Estimation Word-based Graph Asia Automation Data Mining Explosions Information Retrieval Internet Organizing Statistical Distributions Thesauri Training Data
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/13453
专题模式识别国家重点实验室_图像与视频分析
通讯作者Jing Liu
推荐引用方式
GB/T 7714
Jing Liu,Mingjing Li,Qingshan Liu,et al. Image Annotation Refinement using NSC-Based Word Correlation[C],2007.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Jing Liu]的文章
[Mingjing Li]的文章
[Qingshan Liu]的文章
百度学术
百度学术中相似的文章
[Jing Liu]的文章
[Mingjing Li]的文章
[Qingshan Liu]的文章
必应学术
必应学术中相似的文章
[Jing Liu]的文章
[Mingjing Li]的文章
[Qingshan Liu]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。