AI Paper Atlas

Research map / Video / Video segmentation and tracking

MARLIN: Masked Autoencoder for Facial Video Representation LearnINg

Zhixi Cai, Shreya Ghosh, Kalin Stefanov, Abhinav Dhall, Jianfei Cai, Hamid Rezatofighi, Reza Haffari, Munawar Hayat

CVPR 2023 · Video › Video segmentation and tracking · approach: Deepfake video detection · 101 citations (OpenAlex)

Read the paper

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
pre-train with MARLIN rather than VideoMAEViT-B facial video encoder · CMU-MOSEI 7-class sentimentaccuracy: 33.78 -> 34.63Improved
pre-train with MARLIN rather than VideoMAEViT-B facial video encoder · FaceForensics++ (LQ)accuracy: 87.57 -> 89.43Improved
use MARLIN features rather than the Wav2Lip baseline encoderWav2Lip on LRS2 · LRS2FID: 4.887 -> 3.452Improved
add Fasking to VideoMAE pre-training (ablation)ViT-B facial video encoder · CMU-MOSEI 7-class sentimentaccuracy: 33.78 -> 34.58Improved
add Fasking to VideoMAE pre-training (ablation)ViT-B facial video encoder · FaceForensics++accuracy: 87.57 -> 87.29Hurt
add adversarial training to VideoMAE pre-training (ablation)ViT-B facial video encoder · CMU-MOSEI emotionaccuracy: 80.39 -> 80.58Improved
add Fasking and adversarial training (ablation)ViT-B facial video encoder · FaceForensics++accuracy: 87.57 -> 89.43Improved
scale the encoder from ViT-B to ViT-L (ablation)MARLIN · CMU-MOSEI 7-class sentimentaccuracy: 34.63 -> 35.28Improved
replace Fasking with random masking (ablation)MARLIN · FaceForensics++AUC: 0.9305 -> 0.8797Hurt
replace Fasking with frame masking (ablation)MARLIN · CMU-MOSEI emotionaccuracy: 79.33 vs 80.60Hurt
replace Fasking with standard tube masking (ablation)MARLIN · FaceForensics++AUC: 0.9096 vs 0.9305Hurt
use a masking ratio near 90% instead of lower or higher ratios (ablation)MARLIN · CMU-MOSEIaccuracyMixed

Later papers that compared with this method

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

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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