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% for Deepfake and 95% for Face2Face.

https://hal-upec-upem.archives-ouvertes.fr/hal-01867298/document

MesoNet: a Compact Facial Video Forgery Detection Network

MesoNet: a Compact Facial Video Forgery Detection Network.

Validating a given multimedia content is nowadays quite a hard task because of the huge amount of possible alterations that could have been operated on it. In order to face this problem, image and video experts have proposed a wide set of solutions to reconstruct the processing history of a given multimedia signal. These strategies rely on the fact that non-reversible operations applied to a signal leave some traces ("footprints") that can be identified and classified in order to reconstruct the possible alterations that have been operated on the original source. These solutions permit also to identify which source generated a specific image or video content given some device-related peculiarities. The paper aims at providing an overview of the existing video processing techniques, considering all the possible alterations that can be operated on a single signal and also the possibility of identifying the traces that could reveal important information about its origin and use.

/pdf/an-overview-on-video-forensics-20693kkcsx.pdf

An overview on video forensics

The illegal distribution of a digital movie is a common and significant threat to the film industry. With the advent of high-speed broadband Internet access, a pirated copy of a digital video can now be easily distributed to a global audience. A possible means of limiting this type of digital theft is digital video watermarking whereby additional information, called a watermark, is embedded in the host video. This watermark can be extracted at the decoder and used to determine whether the video content is watermarked. This paper presents a review of the digital video watermarking techniques in which their applications, challenges, and important properties are discussed, and categorizes them based on the domain in which they embed the watermark. It then provides an overview of a few emerging innovative solutions using watermarks. Protecting a 3D video by watermarking is an emerging area of research. The relevant 3D video watermarking techniques in the literature are classified based on the image-based representations of a 3D video in stereoscopic, depth-image-based rendering, and multi-view video watermarking. We discuss each technique, and then present a survey of the literature. Finally, we provide a summary of this paper and propose some future research directions.

An Overview of Digital Video Watermarking

Ternary radial harmonic Fourier moments based robust stereo image zero-watermarking algorithm

Monolithic integration of colloidal quantum dot (CQD) thin-film on 200 mm CMOS wafers is demonstrated. Full pixelation of CQD thin-film photodiodes at wafer level is presented for the first time. We show a low-temperature process flow compatible with standard CMOS fab equipment. The self-aligned pixelation approach is an improvement over a conventional way of having a thin-film absorber layer on pixelated bottom electrodes, and it enables crosstalk reduction as well as multi-stack arrays.

Wafer Level Pixelation of Colloidal Quantum Dot Image Sensors

/pdf/semi-supervised-synthetic-to-real-domain-adaptation-for-fine-12gvcgje0b.pdf

Semi-supervised Synthetic-to-Real Domain Adaptation for Fine-grained Naval Ship Image Classification

Recently, the importance of securing data in the field of computer vision using machine learning is increasing. In this situation, research to use synthetic images as training data in fields where real images cannot be used for various reasons is ongoing. In particular, in the defense field, where it is difficult to know the characteristics of imaging devices, neural network learning using synthetic images is essential for the introduction of civilian technology. In this paper, we propose a method to use for object detection neural network training by generating synthetic images instead of real images and removing artifacts from the generated images.

A Study on NeRF-based Synthetic Image Generation and Post-processing Method for Object Detection

Short-wave infrared (SWIR) wavelength range

Jiwon Lee

Papers

Wafer Level Pixelation of Colloidal Quantum Dot Image Sensors

Semi-supervised Synthetic-to-Real Domain Adaptation for Fine-grained Naval Ship Image Classification

A Study on NeRF-based Synthetic Image Generation and Post-processing Method for Object Detection

44.4: Invited Paper: Quantum Dot Infrared Image Sensors for the Future Display Interfaces

Decision Tree-Based Digit Recognition in Basketball Scoreboard Videos