AI Paper Atlas

Research map / Video / Video segmentation and tracking

Two-branch Recurrent Network for Isolating Deepfakes in Videos

Iacopo Masi, Aditya Killekar, Royston Marian Mascarenhas, Shenoy Pratik Gurudatt, Wael AbdAlmageed

ECCV 2020 · Video › Video segmentation and tracking · approach: Deepfake video detection · 494 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 per-layer learning rates, dropout and the new loss to the encoder (ablation)DenseNet encoder · FF++ Deepfakes c40 (no LSTM)tAUC1%: 57.63 -> 76.04Improved
add per-layer learning rates, dropout and the new loss to the encoder (ablation)DenseNet encoder · FF++ Deepfakes c40 (no LSTM)TAR1%: 81.50 -> 92.84Improved
add per-layer learning rates, dropout and the new loss to the encoder (ablation)DenseNet encoder · FF++ Deepfakes c40 (no LSTM)tAUC10%: 86.61 -> 89.91Improved
add the second (LoG) branch to the single RGB branch (ablation)backbone without LSTM · FF++ Deepfakes c23tAUC1%: 56.78 -> 61.70Improved
add the second (LoG) branch to the single RGB branch (ablation)backbone without LSTM · FF++ Deepfakes c23tAUC10%: 61.14 -> 70.80Improved
add the second (LoG) branch to the single RGB branch (ablation)backbone without LSTM · FF++ Deepfakes c23TAR1%: 99.34 -> 98.34Hurt
add dropout/fine-tuning schedule to the LSTM model (ablation)LSTM model · FF++ Deepfakes c40 (with LSTM)tAUC1%: 57.21 -> 73.58Improved
concatenate (cat) bi-directional LSTM outputs instead of summing (ablation)LSTM model · FF++ Deepfakes c40 (with LSTM)tAUC1%: 67.49 -> 73.58Improved
use 128 instead of 256 LSTM hidden nodes (g=2) (ablation)LSTM model · FF++ Deepfakes c40 (with LSTM)tAUC1%: 76.35 -> 81.53Improved
split fusion conv1x1 filters into two groups (g=2 instead of g=1) (ablation)LSTM model · FF++ Deepfakes c40 (with LSTM)tAUC1%: 73.58 -> 81.53Improved
use proposed model instead of Xception at medium compressionFF++ c23 · FaceForensics++ c23 video-levelAUC: 92.50 -> 99.12Improved
use proposed model instead of Xception at c40 for frame-level tAUC10% and pAUC10%FF++ c40 · FaceForensics++ c40 frame-leveltAUC10%: 45.92 -> 40.41Hurt

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