Autoencoder with recurrent neural networks for video forgery detection
By Dario D'Avino, Davide Cozzolino, Giovanni Poggi, Luisa Verdoliva. 2017
102 citations recorded by the source corpus.
Video forgery detection is becoming an important issue in recent years, because modern editing software provide powerful and easy-to-use tools to manipulate videos. In this paper we propose to perform detection by means of deep learning, with an architecture based on autoencoders and recurrent neural networks. A training phase on a few pristine frames allows the autoencoder to learn an intrinsic model of the source. Then, forged material is singled out as anomalous, as it does not fit the learned model, and is encoded with a large reconstruction error. Recursive networks, implemented with the long short-term memory model, are used to exploit temporal dependencies. Preliminary results on forged videos show the potential of this approach.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Jing Shao
- Lu Sheng
- Guojun Yin
- Yuyang Qian
- Luisa Verdoliva
- Dilip Ravi Kiran
- Mathew Thomas
- Ranjith Parakkal
Citations in the corpus
- Media Forensics and DeepFakes: An Overview (2020, methodology): “In [149], the approach has been extended to videos by including a LSTM recurrent network to account for temporal dependencies.”
- Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues (2020, methodology): “essing method, is used to rene and mine underlying subtle information in forgery detection, which leverages existing knowledge of the characteristics of fake images. Some studies use high-pass lters [57,15,29,48], Gabor lters [10,22] etc. to extract features of interest (e.g. edge and texture inform”
- An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos (2018, methodology): “A recurrent autoencoder using an LSTM that models temporal dependence between patches from a sequence of input frames is used to detect video forgery [69].”