MesoNet: a Compact Facial Video Forgery Detection Network

09/04/2018
by   Darius Afchar, et al.
0

This paper presents a method to automatically and efficiently detect face tampering in videos, and particularly focuses on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face. Traditional image forensics techniques are usually not well suited to videos due to the compression that strongly degrades the data. Thus, this paper follows a deep learning approach and presents two networks, both with a low number of layers to focus on the mesoscopic properties of images. We evaluate those fast networks on both an existing dataset and a dataset we have constituted from online videos. The tests demonstrate a very successful detection rate with more than 98

READ FULL TEXT
research
05/17/2020

Detecting Forged Facial Videos using convolutional neural network

In this paper, we propose to detect forged videos, of faces, in online v...
research
08/18/2021

DeepFake MNIST+: A DeepFake Facial Animation Dataset

The DeepFakes, which are the facial manipulation techniques, is the emer...
research
09/10/2021

Detection of GAN-synthesized street videos

Research on the detection of AI-generated videos has focused almost excl...
research
05/02/2019

Recurrent-Convolution Approach to DeepFake Detection - State-Of-Art Results on FaceForensics++

Spread of misinformation has become a significant problem, raising the i...
research
01/21/2020

Detecting Face2Face Facial Reenactment in Videos

Visual content has become the primary source of information, as evident ...
research
06/28/2021

Cheating Detection Pipeline for Online Interviews and Exams

Remote examination and job interviews have gained popularity and become ...
research
04/25/2020

Deepfakes Detection with Automatic Face Weighting

Altered and manipulated multimedia is increasingly present and widely di...

Please sign up or login with your details

Forgot password? Click here to reset