Sharp Multiple Instance Learning for DeepFake Video Detection

Author:

Li Xiaodan1,Lang Yining2,Chen Yuefeng3,Mao Xiaofeng3,He Yuan2,Wang Shuhui4,Xue Hui3,Lu Quan3

Affiliation:

1. Alibaba Group, China, Hangzhou, China

2. Alibaba Group, Beijing, China

3. Alibaba Group, Hangzhou, China

4. Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China

Publisher

ACM

Reference54 articles.

1. MesoNet: a Compact Facial Video Forgery Detection Network

2. Multiple instance classification: Review, taxonomy and comparative study

3. Anonymous. [n.d.]. Example of Partially attacked DeepFake video on Youtube. [EB/OL]. https://www.youtube.com/watch?v=BU9YAHigNx8 Accessed April 4 2020. Anonymous. [n.d.]. Example of Partially attacked DeepFake video on Youtube. [EB/OL]. https://www.youtube.com/watch?v=BU9YAHigNx8 Accessed April 4 2020.

4. Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. In arXiv preprint:1409.0473. Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. In arXiv preprint:1409.0473.

5. A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer

Cited by 112 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. SFormer: An end-to-end spatio-temporal transformer architecture for deepfake detection;Forensic Science International: Digital Investigation;2024-12

2. A systematic literature review on deepfake detection techniques;Multimedia Tools and Applications;2024-08-02

3. Fake news or real? Detecting deepfake videos using geometric facial structure and graph neural network;Technological Forecasting and Social Change;2024-08

4. Towards Unified Defense for Face Forgery and Spoofing Attacks via Dual Space Reconstruction Learning;International Journal of Computer Vision;2024-07-02

5. Fully Unsupervised Deepfake Video Detection Via Enhanced Contrastive Learning;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-07

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3