CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算与图形学
Measuring and Predicting Visual Importance of Similar Objects
Kong, Yan1; Dong, Weiming1; Mei, Xing1; Ma, Chongyang2; Lee, Tong-Yee3; Lyu, Siwei4; Huang, Feiyue5; Zhang, Xiaopeng1
AbstractSimilar objects are ubiquitous and abundant in both natural and artificial scenes. Determining the visual importance of several similar objects in a complex photograph is a challenge for image understanding algorithms. This study aims to define the importance of similar objects in an image and to develop a method that can select the most important instances for an input image from multiple similar objects. This task is challenging because multiple objects must be compared without adequate semantic information. This challenge is addressed by building an image database and designing an interactive system to measure object importance from human observers. This ground truth is used to define a range of features related to the visual importance of similar objects. Then, these features are used in learning-to-rank and random forest to rank similar objects in an image. Importance predictions were validated on 5,922 objects. The most important objects can be identified automatically. The factors related to composition (e.g., size, location, and overlap) are particularly informative, although clarity and color contrast are also important. We demonstrate the usefulness of similar object importance on various applications, including image retargeting, image compression, image re-attentionizing, image admixture, and manipulation of blindness images.
KeywordSimilar Objects Visual Importance Listwise Ranking
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Funding OrganizationNational Natural Science Foundation of China(61271430 ; Supporting Program for Sci & Tech Research of China(2015BAH53F00) ; CASIA-Tencent BestImage joint research project ; Ministry of Science and Technology, Taiwan(MOST-103-2221-E-006-106-MY3 ; National Science Foundation(IIS-0953373 ; 61372184 ; MOST-104-2221-E-006-044-MY3) ; CCF-1319800) ; 61331018 ; 61471359)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Software Engineering
WOS IDWOS:000387360500006
Citation statistics
Cited Times:2[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Corresponding AuthorDong, Weiming
Affiliation1.Chinese Acad Sci, Inst Automat, NLPR LIAMA, Beijing, Peoples R China
2.Univ Southern Calif, Dept Comp Sci, Los Angeles, CA 90089 USA
3.Natl Cheng Kung Univ, Dept Comp Sci & Informat Engn, Tainan, Taiwan
4.SUNY Albany, Dept Comp Sci, Albany, NY 12222 USA
5.Tencent, Social Network Platform Dept, Shanghai, Peoples R China
Recommended Citation
GB/T 7714
Kong, Yan,Dong, Weiming,Mei, Xing,et al. Measuring and Predicting Visual Importance of Similar Objects[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2016,22(12):2564-2578.
APA Kong, Yan.,Dong, Weiming.,Mei, Xing.,Ma, Chongyang.,Lee, Tong-Yee.,...&Zhang, Xiaopeng.(2016).Measuring and Predicting Visual Importance of Similar Objects.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,22(12),2564-2578.
MLA Kong, Yan,et al."Measuring and Predicting Visual Importance of Similar Objects".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 22.12(2016):2564-2578.
Files in This Item: Download All
File Name/Size DocType Version Access License
Measuring and Predic(2594KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Kong, Yan]'s Articles
[Dong, Weiming]'s Articles
[Mei, Xing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Kong, Yan]'s Articles
[Dong, Weiming]'s Articles
[Mei, Xing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Kong, Yan]'s Articles
[Dong, Weiming]'s Articles
[Mei, Xing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Measuring and Predicting Visual Importance of Similar Objects.pdf
Format: Adobe PDF
All comments (0)
No comment.

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