期刊
出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3152118
关键词
Age estimation; deep learning; convolutional networks; expression recognition; multi-task learning; multi-level regression; scattering network; transfer learning
类别
资金
- Ministry of Science and Technology of Taiwan [MOST 105-2218-E-001-006, MOST 106-2221-E-001-016]
This article tackles the problem of joint estimation of human age and facial expression. This is an important yet challenging problem because expressions can alter face appearances in a similar manner to human aging. Different from previous approaches that deal with the two tasks independently, our approach trains a convolutional neural network (CNN) model that unifies ordinal regression and multi-class classification in a single framework. We demonstrate experimentally that our method performs more favorably against state-of-the-art approaches.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据