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. 生物识别与安全技术研究中心
Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis

文献类型：期刊论文

作者Lin, Xuxin2,3,4; Wan, Jun2,3; Xie, Yiliang4; Zhang, Shifeng2,3; Lin, Chi5; Liang, Yanyan4; Guo, Guodong1,6; Li, Stan Z.2,3
刊名IEEE TRANSACTIONS ON CYBERNETICS
出版日期2020-03-01
卷号50期号:3页码:1292-1305
ISSN号2168-2267
关键词Face Task analysis Training Face recognition Facial features Pipelines Attribute analysis face analysis face detection landmark localization multitask learning
DOI10.1109/TCYB.2019.2917049
通讯作者Liang, Yanyan(yyliang@must.edu.mo)
英文摘要Deep multitask learning for face analysis has received increasing attentions. From literature, most existing methods focus on optimizing a main task by jointly learning several auxiliary tasks. It is challenging to consider the performance of each task in a multitask framework due to the following reasons: 1) different face tasks usually rely on different levels of semantic features; 2) each task has different learning convergence rate, which could affect the whole performance when joint training; and 3) multitask model needs rich label information for efficient training, but existing facial datasets provide limited annotations. To address these issues, we propose a task-oriented feature-fused network (TFN) for simultaneously solving face detection, landmark localization, and attribute analysis. In this network, a task-oriented feature-fused block is designed to learn task-specific feature combinations; then, an alternative multitask training scheme is presented to optimize each task with considering of their different learning capacities. We also present a large-scale face dataset called JFA in support of proposed method, which provides multivariate labels, including face bounding box, 68 facial landmarks, and 3 attribute labels (i.e., apparent age, gender, and ethnicity). The experimental results suggest that the TFN outperforms several multitask models on the JFA dataset. Furthermore, our approach achieves competitive performances on WIDER FACE and 300W dataset, and obtains state-of-the-art results for gender recognition on the MORPH II dataset.
资助项目National Key Research and Development Plan[2016YFC0801002] ; Chinese National Natural Science Foundation[61876179] ; Chinese National Natural Science Foundation[61872367] ; Science and Technology Development Fund of Macau[152/2017/A] ; Science and Technology Development Fund of Macau[0025/2018/A1] ; Science and Technology Development Fund of Macau[008/2019/A1]
WOS研究方向Automation & Control Systems ; Computer Science
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000510941100035
资助机构National Key Research and Development Plan ; Chinese National Natural Science Foundation ; Science and Technology Development Fund of Macau
源URL[http://ir.ia.ac.cn/handle/173211/28594]  
专题自动化研究所_模式识别国家重点实验室_生物识别与安全技术研究中心
通讯作者Liang, Yanyan
作者单位1.Baidu Res, Inst Deep Learning, Beijing 100193, Peoples R China
2.Chinese Acad Sci, Inst Automat, Ctr Biometr & Secur Res, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
4.Macau Univ Sci & Technol, Fac Informat Technol, Macau 999078, Peoples R China
5.Univ Southern Calif, USC Viterbi Sch Engn, Los Angeles, CA 90089 USA
6.Baidu Res, Natl Engn Lab Deep Learning Technol & Applicat, Beijing 100193, Peoples R China
推荐引用方式
GB/T 7714		 Lin, Xuxin,Wan, Jun,Xie, Yiliang,et al. Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis[J]. IEEE TRANSACTIONS ON CYBERNETICS,2020,50(3):1292-1305.
APA Lin, Xuxin.,Wan, Jun.,Xie, Yiliang.,Zhang, Shifeng.,Lin, Chi.,...&Li, Stan Z..(2020).Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis.IEEE TRANSACTIONS ON CYBERNETICS,50(3),1292-1305.
MLA Lin, Xuxin,et al."Task-Oriented Feature-Fused Network With Multivariate Dataset for Joint Face Analysis".IEEE TRANSACTIONS ON CYBERNETICS 50.3(2020):1292-1305.

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。