AI Paper Atlas

Research map / Video / Video segmentation and tracking

ID-Reveal: Identity-Aware DeepFake Video Detection

Davide Cozzolino, Andreas Rössler, Justus Thies, Matthias Nießner, Luisa Verdoliva

ICCV 2021 · Video › Video segmentation and tracking · approach: Deepfake video detection · 238 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add adversarial training with 3DMM generative network (ablation)ID-Reveal · DFD FR HQaccuracy (%): 73.8 -> 75.6Improved
add adversarial training with 3DMM generative network (ablation)ID-Reveal · DFD FR LQaccuracy (%): 79.1 -> 81.8Improved
add adversarial training with 3DMM generative network (ablation)ID-Reveal · DFD FS HQaccuracy (%): 82.6 -> 84.8Improved
add adversarial training with 3DMM generative network (ablation)ID-Reveal · DFD FS LQaccuracy (%): 73.0 -> 78.1Improved
add adversarial training (ablation)ID-Reveal · DFD FR (hardest scenario)AUC: further improvement of around 3% for AUCImproved
use proposed loss instead of multi-similarity loss (ablation)ID-Reveal · DFD (HQ/LQ, FR/FS)AUC: 5.5% on averageImproved
use proposed loss instead of triplet loss (ablation)ID-Reveal · DFD (HQ/LQ, FR/FS)AUC: 2.8% on averageImproved
use proposed loss instead of multi-similarity loss, with adversarial (ablation)ID-Reveal · DFD FR LQaccuracy (%): 69.1 -> 81.8Improved
average frame scores instead of taking maximum (ablation)frame-based detectors · DFDAUC: increase in terms of AUC is around 0.04, accuracy increases of about 3%Improved
move from HQ to LQ compressionXception · DFD FSaccuracy (%): 78.5 -> 58.5Hurt
move from HQ to LQ compressionID-Reveal · DFD FSaccuracy (%): 84.8 -> 78.1Hurt
train only on real videos (VoxCeleb2) instead of supervised on DFDCID-Reveal vs Seferbekov · DFD FR HQaccuracy (%): 55.8 -> 75.6Improved

Later papers that compared with this method

1 later accepted paper reports ID-Reveal as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy