In this paper, we propose a new method to expose AI-generated fake face images or videos (commonly known as the Deep Fakes). Our method is based on the observat.

2018年11月1日 · In this paper, we propose a new method to expose AI-generated fake face images or videos (commonly known as the Deep Fakes).

2019年3月30日 · View a PDF of the paper titled Exposing GAN-synthesized Faces Using Landmark Locations, by Xin Yang and Yuezun Li and Honggang Qi and Siwei Lyu

2019年9月27日 · We present a new large-scale challenging DeepFake video dataset, Celeb-DF, which contains 5,639 high-quality DeepFake videos of celebrities generated using improved synthesis process. We conduct a comprehensive evaluation of DeepFake detection methods and datasets to demonstrate the escalated level of challenges posed by Celeb-DF.

2018年11月1日 · Our method is based on the observations that Deep Fakes are created by splicing synthesized face region into the original image, and in doing so, introducing errors that can be revealed when 3D...

Xin Wang Assistant Professor, University at Albany SUNY | AI Plus Institute

Siwei XIN of Central South University, Changsha (CSU) | Read 1 publication | Contact Siwei XIN

From 2023.07, I am an assistant professor at Intelligent Game and Decision Lab, Academy of Military Sciences, Beijing. I graduated from the Department of Computer Science, National …

Request PDF | On May 1, 2019, Xin Yang and others published Exposing Deep Fakes Using Inconsistent Head Poses | Find, read and cite all the research you need on ResearchGate

2024年10月25日 · Xin Yang, Yuezun Li, and Siwei Lyu. Exposing deep fakes using inconsistent head poses. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 8261–8265. IEEE, 2019.