Skip to main navigation Skip to search Skip to main content

Faketalkerdetect: Effective and practical realistic neural talking head detection with a highly unbalanced dataset

  • Department of Artificial Intelligence

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Detecting realistic fake images and videos is an increasingly important and urgent problem because they can be maliciously used. In this work, we propose FakeTalkerDetect, which is based on siamese networks to detect the recently proposed realistic talking head with few-shot learning. Unlike conventional methods, we propose to use pre-trained models with only a few real images for fine-tuning in siamese networks to effectively detect the fake images in a highly unbalanced data setting. Our FakeTalkerDetect achieves the overall accuracy 98.81% accuracy in detecting fake images generated from the latest neural talking head models. In particular, our preliminary work also demonstrates the effectiveness for the highly unbalanced dataset.

Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1285-1287
Number of pages3
ISBN (Electronic)9781728150239
DOIs
StatePublished - Oct 2019
Event17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019 - Seoul, Korea, Republic of
Duration: 27 Oct 201928 Oct 2019

Publication series

NameProceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019

Conference

Conference17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019
Country/TerritoryKorea, Republic of
CitySeoul
Period27/10/1928/10/19

Keywords

  • DeepFake
  • Few shot learning
  • Generative adversarial networks
  • Siamese networks
  • Talking heads

Fingerprint

Dive into the research topics of 'Faketalkerdetect: Effective and practical realistic neural talking head detection with a highly unbalanced dataset'. Together they form a unique fingerprint.

Cite this