Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
| Joint face alignment and segmentation via deep multi-task learning | |
Zhao, Yucheng1,2 ; Tang, Fan1,2; Dong, Weiming1; Huang, Feiyue3; Zhang, Xiaopeng1
| |
| Source Publication | MULTIMEDIA TOOLS AND APPLICATIONS
 |
| ISSN | 1380-7501 |
| 2019-05-01 | |
| Volume | 78Issue:10Pages:13131-13148 |
| Corresponding Author | Dong, Weiming(weiming.dong@ia.ac.cn) |
| Abstract | 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. |
| Keyword | Face alignment Face segmentation Multi-task learning Virtual makeup Face swap |
| DOI | 10.1007/s11042-018-5609-1 |
| Indexed By | SCI |
| Language | 英语 |
| Funding Project | 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 |
| Funding Organization | National Natural Science Foundation of China ; Beijing Natural Science Foundation ; National Key Technology R&D Program of China ; CASIA-Tencent YouTu jointly research project |
| WOS Research Area | Computer Science ; Engineering |
| WOS Subject | Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic |
| WOS ID | WOS:000471654900022 |
| Publisher | SPRINGER |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.ia.ac.cn/handle/173211/20889 |
| Collection | 模式识别国家重点实验室_多媒体计算与图形学 |
| Corresponding Author | Dong, Weiming |
| Affiliation | 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 |
| First Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
| Corresponding Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
| Recommended Citation 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. |
| Files in This Item: | Download All | |||||
| File Name/Size | DocType | Version | Access | License | ||
| Joint face alignment（3380KB） | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | View Download | |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment