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 |
DOI | 10.1007/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。