MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection

In this paper, we present MINTIME, a video deepfake detection method that effectively captures spatial and temporal inconsistencies in videos that depict multiple individuals and varying face sizes. Unlike previous approaches that either employ simplistic a-posteriori aggregation schemes, i.e., aver...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on information forensics and security 2024, Vol.19, p.6084-6096
Hauptverfasser:	Coccomini, Davide Alessandro, Zilos, Giorgos Kordopatis, Amato, Giuseppe, Caldelli, Roberto, Falchi, Fabrizio, Papadopoulos, Symeon, Gennaro, Claudio
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks computer vision Convolutional neural networks Datasets Deception deep learning Deepfake Deepfake detection Deepfakes Embedding Face recognition Faces Invariants Task analysis Transformers Vectors Video vision transformers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!