中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
Image Retargetability

文献类型：期刊论文

作者Tang, Fan2,3; Dong, Weiming2; Meng, Yiping4; Ma, Chongyang5; Wu, Fuzhang6; Li, Xinrui1; Lee, Tong-Yee7
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2020-03-01
卷号22期号:3页码:641-654
ISSN号1520-9210
关键词Visualization Task analysis Distortion Measurement Image resolution Convolutional neural networks Semantics Image retargetability visual attributes multi-task learning deep convolutional neural network
DOI10.1109/TMM.2019.2932620
通讯作者Dong, Weiming(weiming.dong@ia.ac.cn)
英文摘要Real-world applications could benefit from the ability to automatically retarget an image to different aspect ratios and resolutions while preserving its visually and semantically important content. However, not all images can be equally processed. This study introduces the notion of image retargetability to describe how well a particular image can be handled by content-aware image retargeting. We propose to learn a deep convolutional neural network to rank photo retargetability, in which the relative ranking of photo retargetability is directly modeled in the loss function. Our model incorporates the joint learning of meaningful photographic attributes and image content information, which can facilitate the regularization of the complicated retargetability rating problem. To train and analyze this model, we collect a dataset that contains retargetability scores and meaningful image attributes assigned by six expert raters. The experiments demonstrate that our unified model can generate retargetability rankings that are highly consistent with human labels. To further validate our model, we show the applications of image retargetability in retargeting method selection, retargeting method assessment and generating a photo collage.
WOS关键词OBJECTIVE QUALITY ASSESSMENT ; MODEL
资助项目National Key R&D Program of China[2018YFC0807500] ; National Natural Science Foundation of China[61832016] ; National Natural Science Foundation of China[61672520] ; National Natural Science Foundation of China[61702488] ; Ministry of Science and Technology, Taiwan[108-2221-E-006-038-MY3] ; CASIA-Tencent Youtu joint research project
WOS研究方向Computer Science ; Telecommunications
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000519576700006
资助机构National Key R&D Program of China ; National Natural Science Foundation of China ; Ministry of Science and Technology, Taiwan ; CASIA-Tencent Youtu joint research project
源URL[http://ir.ia.ac.cn/handle/173211/38613]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者Dong, Weiming
作者单位1.North China Elect Power Univ, Dept Math & Phys, Beijing 102206, Peoples R China
2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100864, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
4.Didi Chuxing, Beijing 100094, Peoples R China
5.Kuaishou Technol, Beijing 100085, Peoples R China
6.Chinese Acad Sci, Inst Software, Beijing 100864, Peoples R China
7.Natl Cheng Kung Univ, Tainan 701, Taiwan
推荐引用方式
GB/T 7714		 Tang, Fan,Dong, Weiming,Meng, Yiping,et al. Image Retargetability[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2020,22(3):641-654.
APA Tang, Fan.,Dong, Weiming.,Meng, Yiping.,Ma, Chongyang.,Wu, Fuzhang.,...&Lee, Tong-Yee.(2020).Image Retargetability.IEEE TRANSACTIONS ON MULTIMEDIA,22(3),641-654.
MLA Tang, Fan,et al."Image Retargetability".IEEE TRANSACTIONS ON MULTIMEDIA 22.3(2020):641-654.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

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。