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. 多媒体计算与图形学团队
Joint face alignment and segmentation via deep multi-task learning

文献类型：期刊论文

作者Zhao, Yucheng1,2; Tang, Fan1,2; Dong, Weiming1; Huang, Feiyue3; Zhang, Xiaopeng1
刊名MULTIMEDIA TOOLS AND APPLICATIONS
出版日期2019-05-01
卷号78期号:10页码:13131-13148
关键词Face alignment Face segmentation Multi-task learning Virtual makeup Face swap
ISSN号1380-7501
DOI10.1007/s11042-018-5609-1
通讯作者Dong, Weiming(weiming.dong@ia.ac.cn)
英文摘要Face alignment and segmentation are challenging problems which have been extensively studied in the field of multimedia. These two tasks are closely related and their learning processes are supposed to benefit each other. Hence, we present a joint multi-task learning algorithm for both face alignment and segmentation using deep convolutional neural network (CNN). The proposed multi-task learning approach allows CNN model to simultaneously share visual knowledge between different tasks. With a carefully designed refinement residual module, the cross-layer features are fused in a collaborative manner. To the best of our knowledge, this is the first time that face alignment and segmentation are learned together via deep multi-task learning. Our experiments show that learning these two related tasks simultaneously builds a synergy between them, improves the performance of each individual task, and rivals recent approaches. Furthermore, we demonstrate the effectiveness of our model in two practical applications: virtual makeup and face swap.
资助项目National Natural Science Foundation of China[61672520] ; National Natural Science Foundation of China[61702488] ; National Natural Science Foundation of China[61501464] ; National Natural Science Foundation of China[6120106003] ; Beijing Natural Science Foundation[4162056] ; National Key Technology R&D Program of China[2015BAH53F02] ; CASIA-Tencent YouTu jointly research project
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000471654900022
出版者SPRINGER
资助机构National Natural Science Foundation of China ; Beijing Natural Science Foundation ; National Key Technology R&D Program of China ; CASIA-Tencent YouTu jointly research project
源URL[http://ir.ia.ac.cn/handle/173211/20889]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者Dong, Weiming
作者单位1.Chinese Acad Sci, Inst Automat, NLPR LIAMA, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
3.Tencent, YouTu Lab, Shanghai, Peoples R China
推荐引用方式
GB/T 7714		 Zhao, Yucheng,Tang, Fan,Dong, Weiming,et al. Joint face alignment and segmentation via deep multi-task learning[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2019,78(10):13131-13148.
APA Zhao, Yucheng,Tang, Fan,Dong, Weiming,Huang, Feiyue,&Zhang, Xiaopeng.(2019).Joint face alignment and segmentation via deep multi-task learning.MULTIMEDIA TOOLS AND APPLICATIONS,78(10),13131-13148.
MLA Zhao, Yucheng,et al."Joint face alignment and segmentation via deep multi-task learning".MULTIMEDIA TOOLS AND APPLICATIONS 78.10(2019):13131-13148.

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。