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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Mining collaborative spatio-temporal clues for face forgery detection

文献类型：期刊论文

作者Ding, Bo1,2; Fan, Zhenfeng1,2; Zhao, Zejun1,2; Xia, Shihong1,2
刊名MULTIMEDIA TOOLS AND APPLICATIONS
出版日期2023-08-26
页码20
ISSN号1380-7501
关键词Face forgery detection Spatial-temporal clue Low-level feature Collaborative learning Multimodel attention
DOI10.1007/s11042-023-16173-4
英文摘要Face forgery detection has been a widespread issue recently due to the adverse effects of face forgery techniques on social media. The state-of-the-art deep learning based methods commonly employ low-level texture features for face forgery detection, since most face forgery methods have difficulty simulating low-level signals in natural images. However, most existing methods only visit the low-level features from the spatial or temporal perspective. In this work, we revisit the face forgery detection problem from a spatio-temporal perspective to cover both for better generalization performance. Specifically, we propose a Spatio-Temporal Difference Network (STDN) to mine low-level clues for face forgery detection. The network contains three different but complementary branches 1) high-frequency channel difference images, 2) inter-frame residual signals, and 3) raw RGB images. It is able to capture face forgery traces through a three-branch collaborative learning framework. Furthermore, we propose a multimodal attention fusion module to effectively fuse the complementary features from different branches. Through comprehensive experiments on several publicly available datasets, we demonstrate the superior performance of the proposed STDN. The effectiveness of low-level spatio-temporal clues in a collaborative learning framework could potentially guide future work in face forgery detection.
WOS研究方向Computer Science ; Engineering
语种英语
出版者SPRINGER
WOS记录号WOS:001060295500002
源URL[http://119.78.100.204/handle/2XEOYT63/21385]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Xia, Shihong
作者单位1.Univ Chinese Acad Sci, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Ding, Bo,Fan, Zhenfeng,Zhao, Zejun,et al. Mining collaborative spatio-temporal clues for face forgery detection[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2023:20.
APA Ding, Bo,Fan, Zhenfeng,Zhao, Zejun,&Xia, Shihong.(2023).Mining collaborative spatio-temporal clues for face forgery detection.MULTIMEDIA TOOLS AND APPLICATIONS,20.
MLA Ding, Bo,et al."Mining collaborative spatio-temporal clues for face forgery detection".MULTIMEDIA TOOLS AND APPLICATIONS (2023):20.

入库方式： OAI收割

来源：计算技术研究所

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。