Label Distribution-Based Facial Attractiveness Computation by Deep Residual Learning
Yang-Yu Fan1; Shu Liu1; Bo Li1; Zhe Guo1; Ashok Samal2; Jun Wan3; Stan Z. Li3
2017
发表期刊IEEE TRANSACTIONS ON MULTIMEDIA
期号pp页码:1-13
摘要Two key challenges lie in the facial attractiveness computation research: the lack of discriminative face representations, and the scarcity of sufficient and complete training data. Motivated by recent promising work in face recognition using deep neural networks to learn effective features, the first challenge is expected to be addressed from a deep learning point of view. A very deep residual network is utilized to enable automatic learning of hierarchical aesthetics representation. The inspiration to deal with the second challenge comes from the natural representation of the training data, whereby each training face can be associated with a label (score) distribution given by human raters rather than a single label (average score). This paper, therefore, recasts facial attractiveness computation as a label distribution learning problem. Integrating these two ideas, an end-to-end attractiveness learning framework is established. We also perform feature-level fusion by incorporating the lowlevel geometric features to further improve the computational performance. Extensive experiments are conducted on a standard benchmark, the SCUT-FBP dataset, where our approach shows significant advantages over other state-of-the-art work.; Two key challenges lie in the facial attractiveness computation research: the lack of discriminative face representations, and the scarcity of sufficient and complete training data. Motivated by recent promising work in face recognition using deep neural networks to learn effective features, the first challenge is expected to be addressed from a deep learning point of view. A very deep residual network is utilized to enable automatic learning of hierarchical aesthetics representation. The inspiration to deal with the second challenge comes from the natural representation of the training data, whereby each training face can be associated with a label (score) distribution given by human raters rather than a single label (average score). This paper, therefore, recasts facial attractiveness computation as a label distribution learning problem. Integrating these two ideas, an end-to-end attractiveness learning framework is established. We also perform feature-level fusion by incorporating the lowlevel geometric features to further improve the computational performance. Extensive experiments are conducted on a standard benchmark, the SCUT-FBP dataset, where our approach shows significant advantages over other state-of-the-art work.
关键词Facial Attractiveness Computation Deep Residual Network Label Distribution Feature Fusion Scut-fbp
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/19773
专题模式识别国家重点实验室_生物识别与安全技术研究
作者单位1.Northwestern Polytechnical University
2.University of Nebraska-Lincoln
3.NLPR, CASIA
推荐引用方式
GB/T 7714
Yang-Yu Fan,Shu Liu,Bo Li,et al. Label Distribution-Based Facial Attractiveness Computation by Deep Residual Learning[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2017(pp):1-13.
APA Yang-Yu Fan.,Shu Liu.,Bo Li.,Zhe Guo.,Ashok Samal.,...&Stan Z. Li.(2017).Label Distribution-Based Facial Attractiveness Computation by Deep Residual Learning.IEEE TRANSACTIONS ON MULTIMEDIA(pp),1-13.
MLA Yang-Yu Fan,et al."Label Distribution-Based Facial Attractiveness Computation by Deep Residual Learning".IEEE TRANSACTIONS ON MULTIMEDIA .pp(2017):1-13.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
TMM2017_attractive.p(1377KB)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
[Yang-Yu Fan]的文章
[Shu Liu]的文章
[Bo Li]的文章
百度学术
百度学术中相似的文章
[Yang-Yu Fan]的文章
[Shu Liu]的文章
[Bo Li]的文章
必应学术
必应学术中相似的文章
[Yang-Yu Fan]的文章
[Shu Liu]的文章
[Bo Li]的文章
相关权益政策
暂无数据
收藏/分享
文件名: TMM2017_attractive.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。