Self-Supervised Video Forensics by Audio-Visual Anomaly Detection
Authors:
Top Cited Papers
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10491-10503
Abstract
Manipulated videos often contain subtle inconsistencies between their visual and audio signals. We propose a video forensics method, based on anomaly detection, that can identify these inconsistencies, and that can be trained solely using real, unlabeled data. We train an autoregressive model to generate sequences of audio-visual features, using feature sets that capture the temporal synchronization between video frames and sound. At test time, we then flag videos that the model assigns low probability. Despite being trained entirely on real videos, our model obtains strong performance on the task of detecting manipulated speech videos. Project site: https://cfeng16.github.io/audio-visual-forensics.Keywords
All Related Versions
This publication has 58 references indexed in Scilit:
- Fast Face-Swap Using Convolutional Neural Networks2017
- Tampering Detection and Localization Through Clustering of Camera-Based CNN Features2017
- Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery2017
- Autoencoder with recurrent neural networks for video forgery detectionElectronic Imaging, 2017
- Single-image splicing localization through autoencoder-based anomaly detection2016
- Deep Residual Learning for Image Recognition2016
- Return of the Devil in the Details: Delving Deep into Convolutional Nets2014
- Audio forensics from acoustic reverberation2010
- ImageNet: A large-scale hierarchical image database2009
- The generalized correlation method for estimation of time delayIEEE Transactions on Acoustics, Speech, and Signal Processing, 1976