MSVT: Multiple Spatiotemporal Views Transformer for DeepFake Video Detection-Reference-Cited by-同舟云学术

MSVT: Multiple Spatiotemporal Views Transformer for DeepFake Video Detection

Author:

Yu Yang¹^ORCID,Ni Rongrong¹^ORCID,Zhao Yao¹^ORCID,Yang Siyuan²^ORCID,Xia Fen³,Jiang Ning³,Zhao Guoqing³

Affiliation:

1. Institute of Information Science, Beijing Jiaotong University, Beijing, China

2. Rapid-Rich Object Search Laboratory, Interdisciplinary Graduate Program, Nanyang Technological University, Jurong West, Singapore

3. Mashang Consumer Finance Company Ltd., Chongqing, China

Funder

National Key Research and Development Program of China

National NSF of China

Beijing NSF

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Electrical and Electronic Engineering,Media Technology

Link

Reference78 articles.

3. Exposing deepfake videos by detecting face warping artifacts;li;Proc IEEE Conf Comp Vis Pattern Recognit,2019

Cited by 6 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

3. LLM-Enhanced Deepfake Detection: Dense CNN and Multi-Modal Fusion Framework for Precise Multimedia Authentication;2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS);2024-04-18

5. Guest Editorial Introduction to the Special Issue on Video Transformers;IEEE Transactions on Circuits and Systems for Video Technology;2023-09