Spatio-temporal Features for Generalized Detection of Deepfake Videos

10/22/2020
by   Ipek Ganiyusufoglu, et al.
0

For deepfake detection, video-level detectors have not been explored as extensively as image-level detectors, which do not exploit temporal data. In this paper, we empirically show that existing approaches on image and sequence classifiers generalize poorly to new manipulation techniques. To this end, we propose spatio-temporal features, modeled by 3D CNNs, to extend the generalization capabilities to detect new sorts of deepfake videos. We show that spatial features learn distinct deepfake-method-specific attributes, while spatio-temporal features capture shared attributes between deepfake methods. We provide an in-depth analysis of how the sequential and spatio-temporal video encoders are utilizing temporal information using DFDC dataset arXiv:2006.07397. Thus, we unravel that our approach captures local spatio-temporal relations and inconsistencies in the deepfake videos while existing sequence encoders are indifferent to it. Through large scale experiments conducted on the FaceForensics++ arXiv:1901.08971 and Deeper Forensics arXiv:2001.03024 datasets, we show that our approach outperforms existing methods in terms of generalization capabilities.

READ FULL TEXT

page 2

page 3

page 4

page 8

research
04/21/2022

A Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions

Spatio-temporal action detection is an important and challenging problem...
research
05/13/2022

The Effectiveness of Temporal Dependency in Deepfake Video Detection

Deepfakes are a form of synthetic image generation used to generate fake...
research
06/18/2020

Learning non-rigid surface reconstruction from spatio-temporal image patches

We present a method to reconstruct a dense spatio-temporal depth map of ...
research
07/21/2022

Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption

Despite encouraging progress in deepfake detection, generalization to un...
research
06/13/2013

Learning to encode motion using spatio-temporal synchrony

We consider the task of learning to extract motion from videos. To this ...
research
09/21/2016

Spatio-Temporal Sentiment Hotspot Detection Using Geotagged Photos

We perform spatio-temporal analysis of public sentiment using geotagged ...
research
08/06/2018

Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning

Deep neural networks are efficient learning machines which leverage upon...

Please sign up or login with your details

Forgot password? Click here to reset