CASIA OpenIR  > 智能感知与计算研究中心
Deep Aesthetic Quality Assessment With Semantic Information
Yueying Kao1,2,3; Ran He1,3,4; Kaiqi Huang1,2,3,4
2017-03-01
发表期刊IEEE TRANSACTIONS ON IMAGE PROCESSING
卷号26期号:3页码:1482-1495
文章类型Article
摘要Human beings often assess the aesthetic quality of an image coupled with the identification of the image's semantic content. This paper addresses the correlation issue between automatic aesthetic quality assessment and semantic recognition. We cast the assessment problem as the main task among a multi-task deep model, and argue that semantic recognition task offers the key to address this problem. Based on convolutional neural networks, we employ a single and simple multi-task framework to efficiently utilize the supervision of aesthetic and semantic labels. A correlation item between these two tasks is further introduced to the framework by incorporating the inter-task relationship learning. This item not only provides some useful insight about the correlation but also improves assessment accuracy of the aesthetic task. In particular, an effective strategy is developed to keep a balance between the two tasks, which facilitates to optimize the parameters of the framework. Extensive experiments on the challenging Aesthetic Visual Analysis dataset and Photo. net dataset validate the importance of semantic recognition in aesthetic quality assessment, and demonstrate that multi-task deep models can discover an effective aesthetic representation to achieve the state-of-the-art results.
关键词Visual Aesthetic Quality Assessment Semantic Information Multi-task Learning
WOS标题词Science & Technology ; Technology
DOI10.1109/TIP.2017.2651399
关键词[WOS]HUMAN VISUAL-SYSTEM ; PHOTO ; PREDICTION ; VIDEO ; MODEL
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China(61322209 ; International Partnership Program of Chinese Academy of Science(173211KYSB20160008) ; 61673375 ; 61403387)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000395837700033
引用统计
被引频次:5[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/14377
专题智能感知与计算研究中心
作者单位1.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Yueying Kao,Ran He,Kaiqi Huang. Deep Aesthetic Quality Assessment With Semantic Information[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2017,26(3):1482-1495.
APA Yueying Kao,Ran He,&Kaiqi Huang.(2017).Deep Aesthetic Quality Assessment With Semantic Information.IEEE TRANSACTIONS ON IMAGE PROCESSING,26(3),1482-1495.
MLA Yueying Kao,et al."Deep Aesthetic Quality Assessment With Semantic Information".IEEE TRANSACTIONS ON IMAGE PROCESSING 26.3(2017):1482-1495.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
TIP2017_KAOYUEYING.p(2856KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
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
[Yueying Kao]的文章
[Ran He]的文章
[Kaiqi Huang]的文章
百度学术
百度学术中相似的文章
[Yueying Kao]的文章
[Ran He]的文章
[Kaiqi Huang]的文章
必应学术
必应学术中相似的文章
[Yueying Kao]的文章
[Ran He]的文章
[Kaiqi Huang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: TIP2017_KAOYUEYING.pdf
格式: Adobe PDF
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。