Knowledge Commons of Institute of Automation,CAS
Deeply-learned Hybrid Representations for Facial Age Estimation | |
Zichang Tan1,2![]() ![]() ![]() | |
2019-08 | |
会议名称 | Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) |
会议日期 | 2019-8 |
会议地点 | 澳门 |
摘要 | In this paper, we propose a novel unified network named Deep Hybrid-Aligned Architecture for facial age estimation. It contains global, local and global-local branches. They are jointly optimized and thus can capture multiple types of features with complementary information. In each branch, we employ a separate loss for each sub-network to extract the independent features and use a recurrent fusion to explore correlations among those region features. Considering that the pose variations may lead to misalignment in different regions, we design an Aligned Region Pooling operation to generate aligned region features. Moreover, a new large age dataset named Web-FaceAge owning more than 120K samples is collected under diverse scenes and spanning a large age range. Experiments on five age benchmark datasets, including Web-FaceAge, Morph, FG-NET, CACD and Chalearn LAP 2015, show that the proposed method outperforms the state-of-the-art approaches significantly. |
关键词 | Deep Learning, Facial Age Estimation |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
DOI | https://doi.org/10.24963/ijcai.2019/492 |
URL | 查看原文 |
收录类别 | EI |
七大方向——子方向分类 | 生物特征识别 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44367 |
专题 | 多模态人工智能系统全国重点实验室_生物识别与安全技术 |
通讯作者 | Jun Wan |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences (CASIA) 2.University of Chinese Academy of Sciences 3.Institute of Deep Learning, Baidu Research 4.National Engineering Laboratory for Deep Learning Technology and Application 5.Faculty of Information Technology, Macau University of Science and Technology |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zichang Tan,Yang Yang,Jun Wan,et al. Deeply-learned Hybrid Representations for Facial Age Estimation[C],2019. |
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 | ||
IJCAI19.pdf(2964KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论