English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deepfakes are the synthesized digital media in order to createultra-realistic fake videos to trick the spectator. Deep generative algorithms,such as, Generative Adversarial Networks(GAN) are widely used to accomplishsuch tasks. This approach synthesizes pseudo-realistic contents that are verydifficult to distinguish by traditional detection methods. In most cases,Convolutional Neural Network(CNN) based discriminators are being used fordetecting such synthesized media. However, it emphasise primarily on thespatial attributes of individual video frames, thereby fail to learn thetemporal information from their inter-frame relations. In this paper, weleveraged an optical flow based feature extraction approach to extract thetemporal features, which are then fed to a hybrid model for classification.This hybrid model is based on the combination of CNN and recurrent neuralnetwork (RNN) architectures. The hybrid model provides effective performance onopen source data-sets such as, DFDC, FF++ and Celeb-DF. This proposed methodshows an accuracy of 66.26%, 91.21% and 79.49% in DFDC, FF++, and Celeb-DFrespectively with a very reduced No of sample size of approx 100samples(frames). This promises early detection of fake contents compared toexisting modalities.

A Hybrid CNN-LSTM model for Video Deepfake Detection by Leveraging Optical Flow Features