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. 视频内容安全团队
Face swapping detection based on identity spatial constraints with weighted frequency division

文献类型：期刊论文

作者Ai, Zupeng3; Peng, Chengwei2; Jiang, Jun1; Li, Zekun2; Li, Bing1,4
刊名MULTIMEDIA SYSTEMS
出版日期2022-10-14
页码14
关键词Face swapping Face manipulation Frequency division Identity constraints
ISSN号0942-4962
DOI10.1007/s00530-022-01007-4
通讯作者Li, Zekun(zekun0227@163.com)
英文摘要The generalization of face swapping detectors is necessary when applied to the practical applications. Although the most existing methods may achieve accuracy detection performance on the known forgeries, they fail to make the prediction when faced with unseen face manipulation methods. To alleviate the problem, we propose a novel and practical framework called Detection based on Identity Spatial Constraints with Weighted Frequency Division (DISC-WFD) through introducing the reference image, consisting of the backbone network, the shared Identity Semantic Encoder (ISE) and the corresponding Identity Spatial Constraint (ISC) branches. The ISE is utilized to measure the identity similarity between the input image and the reference image and generates identity spatial constraints. The constraints are imposed on ISC to focus on the high frequency and low-frequency identity-related areas for the discriminative information. The proposed method can significantly improve the performance and the generalization against the unseen manipulation methods. Furthermore, the cross-dataset experiments validate the superiority and the effectiveness of the DISC-WFD.
资助项目National Key Research and Development Program of China[2020AAA0106800] ; National Natural Science Foundation of China[62192785] ; National Natural Science Foundation of China[61902401] ; National Natural Science Foundation of China[61972071] ; National Natural Science Foundation of China[U1936204] ; National Natural Science Foundation of China[62122086] ; National Natural Science Foundation of China[62036011] ; National Natural Science Foundation of China[62192782] ; National Natural Science Foundation of China[61721004] ; Beijing Natural Science Foundation[M22005] ; CAS Key Research Program of Frontier Sciences[QYZDJ-SSW-JSC040] ; Youth Innovation Promotion Association, CAS
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000868236300001
出版者SPRINGER
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; CAS Key Research Program of Frontier Sciences ; Youth Innovation Promotion Association, CAS
源URL[http://ir.ia.ac.cn/handle/173211/50293]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
通讯作者Li, Zekun
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Coordinat Ctr China, Natl Comp Network Emergency Response Tech Team, Beijing 100029, Peoples R China
3.Univ Chinese Acad Sci, Sch Econ & Management, Beijing 100049, Peoples R China
4.People AI Inc, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714		 Ai, Zupeng,Peng, Chengwei,Jiang, Jun,et al. Face swapping detection based on identity spatial constraints with weighted frequency division[J]. MULTIMEDIA SYSTEMS,2022:14.
APA Ai, Zupeng,Peng, Chengwei,Jiang, Jun,Li, Zekun,&Li, Bing.(2022).Face swapping detection based on identity spatial constraints with weighted frequency division.MULTIMEDIA SYSTEMS,14.
MLA Ai, Zupeng,et al."Face swapping detection based on identity spatial constraints with weighted frequency division".MULTIMEDIA SYSTEMS (2022):14.

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。