Unit-Selection Based Facial Video Manipulation Detection

Zusammenfassung
Advancements in video synthesis technology have caused major concerns over the authenticity of audio-visual content. A video manipulation method that is often overlooked is inter-frame forgery, in which segments (or units) of an original video are reordered and rejoined while cut-points are covered with transition effects. Subjective tests have shown the susceptibility of viewers in mistaking such content as authentic. In order to support research on the detection of such manipulations, we introduce a large-scale dataset of 1000 morph-cut videos that were generated by automation of the popular video editing software Adobe Premiere Pro. Furthermore, we propose a novel differential detection pipeline and achieve an outstanding frame-level detection accuracy of 95%.
  • Vollständige Referenz
  • BibTeX
Nielsen, V., Khodabakhsh, A. & Busch, C., (2020). Unit-Selection Based Facial Video Manipulation Detection. In: Brömme, A., Busch, C., Dantcheva, A., Raja, K., Rathgeb, C. & Uhl, A. (Hrsg.), BIOSIG 2020 - Proceedings of the 19th International Conference of the Biometrics Special Interest Group. Bonn: Gesellschaft für Informatik e.V.. (S. 87-96).
@inproceedings{mci/Nielsen2020,
author = {Nielsen, V AND Khodabakhsh, Ali AND Busch, Christoph},
title = {Unit-Selection Based Facial Video Manipulation Detection},
booktitle = {BIOSIG 2020 - Proceedings of the 19th International Conference of the Biometrics Special Interest Group},
year = {2020},
editor = {Brömme, Arslan AND Busch, Christoph AND Dantcheva, Antitza AND Raja, Kiran AND Rathgeb, Christian AND Uhl, Andreas} ,
pages = { 87-96 },
publisher = {Gesellschaft für Informatik e.V.},
address = {Bonn}
}
DateienGroesseFormatAnzeige
BIOSIG_2020_paper_6_update.pdf1.721Mb PDF Öffnen

Haben Sie fehlerhafte Angaben entdeckt? Sagen Sie uns Bescheid: Feedback abschicken