Konferenzbeitrag
Unit-Selection Based Facial Video Manipulation Detection
Lade...
Volltext URI
Dokumententyp
Text/Conference Paper
Zusatzinformation
Datum
2020
Autor:innen
Zeitschriftentitel
ISSN der Zeitschrift
Bandtitel
Verlag
Gesellschaft für Informatik e.V.
Zusammenfassung
Advancements in video synthesis technology have caused major concerns over the authenticityof audio-visual content. A video manipulation method that is often overlooked is inter-frameforgery, in which segments (or units) of an original video are reordered and rejoined while cut-pointsare covered with transition effects. Subjective tests have shown the susceptibility of viewers in mistakingsuch 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 ofthe popular video editing software Adobe Premiere Pro. Furthermore, we propose a novel differentialdetection pipeline and achieve an outstanding frame-level detection accuracy of 95%.
Beschreibung
Nielsen, V; Khodabakhsh, Ali; Busch, Christoph (2020): Unit-Selection Based Facial Video Manipulation Detection. BIOSIG 2020 - Proceedings of the 19th International Conference of the Biometrics Special Interest Group. Bonn: Gesellschaft für Informatik e.V.. PISSN: 1617-5468. ISBN: 978-3-88579-700-5. pp. 87-96. Regular Research Papers. International Digital Conference. 16.-18. September 2020