pith. sign in

arxiv: 1806.02877 · v2 · pith:WGRVQZSSnew · submitted 2018-06-07 · 💻 cs.CV

In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking

Yuezun Li , Ming-Ching Chang , Siwei Lyu This is my paper
classification 💻 cs.CV
keywords videosfakefacegeneratedmethodblinkingdetectingdetection
0
0 comments X
read the original abstract

The new developments in deep generative networks have significantly improve the quality and efficiency in generating realistically-looking fake face videos. In this work, we describe a new method to expose fake face videos generated with neural networks. Our method is based on detection of eye blinking in the videos, which is a physiological signal that is not well presented in the synthesized fake videos. Our method is tested over benchmarks of eye-blinking detection datasets and also show promising performance on detecting videos generated with DeepFake.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Towards Reliable Online Clickbait Video Detection: A Content-Agnostic Approach

    cs.SI 2019-07 unverdicted novelty 5.0

    OVCP uses audience comments to detect clickbait videos without analyzing content, outperforming baselines and humans on YouTube data.

  2. Towards Generalizable Deepfake Image Detection with Vision Transformers

    cs.CV 2026-04 unverdicted novelty 4.0

    Ensemble of vision transformers reaches 96.77% AUC and 9% EER on DF-Wild deepfake test set, outperforming the prior Effort baseline by 7% AUC and 8% EER.