CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 多媒体计算
Content-Based Visual Summarization for Image Collections
Pan, Xingjia1,2; Tang, Fan3; Dong, Weiming1; Ma, Chongyang6; Meng, Yiping7; Huang, Feiyue4; Lee, Tong-yee5; Xu, Changsheng1,2
Source PublicationIEEE Transactions on Visualization and Computer Graphics
2019-10-23
Issue0Pages:1-1
Abstract

With the surge of images in the information era, people demand an effective and accurate way to access meaningful visual information. Accordingly, effective and accurate communication of information has become indispensable. In this work, we propose a content-based approach that automatically generates a clear and informative visual summarization based on design principles and cognitive psychology to represent image collections. We first introduce a novel method to make representative and nonredundant summarizations of image collections, thereby ensuring data cleanliness and emphasizing important information. Then, we propose a tree-based algorithm with a two-step optimization strategy to generate the final layout that operates as follows: (1) an initial layout is created by constructing a tree randomly based on the grouping results of the input image set; (2) the layout is refined through a coarse adjustment in a greedy manner, followed by gradient backpropagation drawing on the training procedure of neural networks. We demonstrate the usefulness and effectiveness of our method via extensive experimental results and user studies. Our visual summarization algorithm can precisely and efficiently capture the main content of image collections better than alternative methods or commercial tools.

KeywordCollage layout hidden-topic tree-based content-aware summeration
MOST Discipline Catalogue工学
DOI10.1109/TVCG.2019.2948611
Indexed BySCI
Language英语
WOS IDWOS:000623420400004
Sub direction classification图像视频处理与分析
Citation statistics
Cited Times:9[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/41614
Collection多模态人工智能系统全国重点实验室_多媒体计算
Corresponding AuthorDong, Weiming
Affiliation1.NLPR, Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.Jilin University
4.Youtu Lab, Tencent
5.National Cheng-Kung University
6.YLab, Kuaishou Technology
7.Didi Chuxing
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Pan, Xingjia,Tang, Fan,Dong, Weiming,et al. Content-Based Visual Summarization for Image Collections[J]. IEEE Transactions on Visualization and Computer Graphics,2019(0):1-1.
APA Pan, Xingjia.,Tang, Fan.,Dong, Weiming.,Ma, Chongyang.,Meng, Yiping.,...&Xu, Changsheng.(2019).Content-Based Visual Summarization for Image Collections.IEEE Transactions on Visualization and Computer Graphics(0),1-1.
MLA Pan, Xingjia,et al."Content-Based Visual Summarization for Image Collections".IEEE Transactions on Visualization and Computer Graphics .0(2019):1-1.
Files in This Item: Download All
File Name/Size DocType Version Access License
VisualSum.pdf(26249KB)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
[Pan, Xingjia]'s Articles
[Tang, Fan]'s Articles
[Dong, Weiming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Pan, Xingjia]'s Articles
[Tang, Fan]'s Articles
[Dong, Weiming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Pan, Xingjia]'s Articles
[Tang, Fan]'s Articles
[Dong, Weiming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: VisualSum.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.