Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MARLIN (ViT-L)

MARLIN (ViT-L)

Reported on 8 benchmarks across 8 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Text ClassificationonCMU-MOSEI
Accuracy· 2022-11-12
80.63
SOTA
MARLIN: Masked Autoencoder for facial video Representation LearnINg arXiv:2211.06627
Emotion ClassificationonCMU-MOSEI
Accuracy· 2022-11-12
80.63
SOTA
MARLIN: Masked Autoencoder for facial video Representation LearnINg arXiv:2211.06627
Sentiment AnalysisonCMU-MOSEI
Accuracy· 2022-11-12
74.83
best: 88.62 (SeMUL-PCD)
MARLIN: Masked Autoencoder for facial video Representation LearnINg arXiv:2211.06627

Methodology3 results

ClassificationonCMU-MOSEI
Accuracy· 2022-11-12
80.63
SOTA
MARLIN: Masked Autoencoder for facial video Representation LearnINg arXiv:2211.06627
3D ReconstructiononFaceForensics++
AUC· 2022-11-12
0.9377
best: 0.956 (QAD-E)
MARLIN: Masked Autoencoder for facial video Representation LearnINg arXiv:2211.06627
3DonFaceForensics++
AUC· 2022-11-12
0.9377
best: 0.956 (QAD-E)
MARLIN: Masked Autoencoder for facial video Representation LearnINg arXiv:2211.06627

Audio1 result

DeepFake DetectiononFaceForensics++
AUC· 2022-11-12
0.9377
best: 0.956 (QAD-E)
MARLIN: Masked Autoencoder for facial video Representation LearnINg arXiv:2211.06627

Medical1 result

3D Shape Reconstruction from VideosonFaceForensics++
AUC· 2022-11-12
0.9377
best: 0.956 (QAD-E)
MARLIN: Masked Autoencoder for facial video Representation LearnINg arXiv:2211.06627