CoChat

MARLIN: Masked Autoencoder for facial video Representation LearnINg

Open access
Cai, Zhixi, Ghosh, Shreya, Stefanov, Kalin, Dhall, Abhinav, Cai, Jianfei, Rezatofighi, Hamid, Haffari, Reza, Hayat, Munawar · 2023 · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Cited by 109

The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.

Abstract

This paper proposes a self-supervised approach to learn universal facial representations from videos, that can transfer across a variety of facial analysis tasks such as Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization (LS). Our proposed framework, named MARLIN, is a facial video masked autoencoder, that learns highly robust and generic facial embeddings from abundantly available non-annotated web crawled facial videos. As a challenging auxiliary task, MARLIN reconstructs the spatio-temporal details of the face from the densely masked facial regions which mainly include eyes, nose, mouth, lips, and skin to capture local and global aspects that in turn help in encoding generic and transferable features. Through a variety of experiments on diverse downstream tasks, we demonstrate MARLIN to be an excellent facial video encoder as well as feature extractor, that performs consistently well across a variety of downstream tasks including FAR (1.13% gain over supervised benchmark), FER (2.64% gain over unsupervised benchmark), DFD (1.86% gain over unsupervised benchmark), LS (29.36% gain for Frechet Inception Distance), and even in low data regime. Our code and models are available at https://github.com/ControlNet/MARLIN.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52729.2023.00150

Cites

41 of 41 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 41 references

Research works printed but not linked: 47

  1. qiu, 0, Learning Spatio-Temporal Representation With Pseudo-3D Residual Net-works, Proceedings of the IEEE International Conference on Computer Vision, 5533
  2. paszke, 2019, PyTorch: An Imperative Style, High-Performance Deep Learning Library, Advances in neural information processing systems, 32
  3. bulat, 2022, Pre-training strategies and datasets for facial representation learning
  4. 10.5244/C.29.41 · DOI · Paper page
  5. chen, 0, Generative Pre-training From Pixels, Proceedings of the 37th International Conference on Machine Learning, 1691
  6. 10.1109/CVPR46437.2021.00574 · DOI · Paper page
  7. chen, 2020, Big Self-Supervised Models are Strong Semi-Supervised Learners, Advances in neural information processing systems, 33, 22243
  8. chen, 0, A Simple Framework for Contrastive Learning of Visual Representations, International Conference on Machine Learning, 1597
  9. 10.1109/ICCV.2015.425 · DOI · Paper page
  10. korshunov, 2018, DeepFakes: a New Threat to Face Recognition?, Assessment and Detection
  11. koromilas, 2022, Un-supervised Multimodal Language Representations using Convolutional Autoencoders
  12. 10.1109/TAFFC.2020.2981446 · DOI · Paper page
  13. prajwal, 2019, Towards Automatic Face-to-Face Translation, Proceedings of the 27th ACM International Conference on Multimedia MM '19, 1428
  14. zhuang, 0, Few-Shot Knowledge Trans-fer for Fine-Grained Cartoon Face Generation, 2021 IEEE International Conference on Multimedia and Expo (ICME), 1
  15. 10.1007/s11263-019-01150-y · DOI · Paper page
  16. zhu, 2022, Celebv-hq A large-scale video facial attributes dataset
  17. 10.4108/eai.14-4-2021.169187 · DOI
  18. 10.1109/CVPR52688.2022.00476 · DOI · Paper page
  19. 10.1109/CVPR42600.2020.00615 · DOI
  20. 10.1007/s00521-019-04559-1 · DOI
  21. aneja, 2020, Generalized Zero and Few-Shot Transfer for Facial Forgery Detection
  22. baevski, 2022, data2vec: A General Frame-work for Self-supervised Learning in Speech, Language of Vision
  23. arjovsky, 0, Wasserstein Generative Adversarial Networks, Proceedings of the 34th International Conference on Machine Learning, 214
  24. yu, 0, Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks, International Conference on Learning Representations
  25. 10.1109/CVPR52688.2022.01814 · DOI · Paper page
  26. 10.1609/aaai.v32i1.12024 · DOI · Paper page
  27. 10.1109/CVPR52688.2022.00943 · DOI · Paper page
  28. hao, 2021, GANcraft Unsupervised 3D Neural Rendering of Minecraft Worlds
  29. wu, 0, ReenactGAN: Learning to Reenact Faces via Boundary Transfer, Proceedings of the European con-ference on computer vision (ECCV), 603
  30. 10.1109/CVPR.2011.5995566 · DOI · Paper page
  31. haugh, 2009, Face and Interaction, Face Communication and Social Interaction, 1
  32. feichtenhofer, 2022, Masked autoencoders as spatiotemporal learners
  33. 10.1145/3474085.3478324 · DOI · Paper page
  34. wang, 2022, Attention-Based Lip Audio-Visual Synthe-sis for Talking Face Generation in the Wild
  35. 10.1109/ICIP.2018.8451242 · DOI
  36. 10.3390/electronics9081188 · DOI · Paper page
  37. huang, 0, Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments, Workshop on Faces in ‘Real-Life’ Images Detection Alignment and Recognition
  38. 10.1038/s41562-021-01097-6 · DOI · Paper page
  39. 10.18653/v1/2020.challengehml-1.1 · DOI
  40. sun, 2022, M$A3$Video Masked Motion Modeling for Self-Supervised Video Representation Learning
  41. chung, 2017, Lip reading in profile, 2017 British Machine Vision Conference
  42. 10.1109/CVPR.2017.195 · DOI · Paper page
  43. 10.1109/CVPR46437.2021.01174 · DOI
  44. donahue, 2019, Large Scale Adversar-ial Representation Learning, Advances in Neural Infor-Mation Processing Systems, 32
  45. el-nouby, 2021, Are large-scale datasets necessary for self-supervised pre-training?
  46. radford, 2016, Unsu-pervised Representation Learning with Deep Convolutional Generative Adversarial Networks, 4th International Con-ference on Learning Representations ICLR 2016
  47. rahmouni, 0, Distinguishing computer graphics from natu-ral images using convolution neural networks, Information Forensics and Security (WIFS) 2017 IEEE International Workshop, 1

Cited by

See all 109

Metadata

Authors
Cai, Z., Ghosh, S., Stefanov, K., Dhall, A., Cai, J., Rezatofighi, H., Haffari, R., & Hayat, M.
Venue
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2023-06
Pages
1493-1504
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4386076638
Cited by
109
References
41
FWCI
12.39
Type
conference paper
Language
en
Open access
green
Funders
DARPA (HROOl122C0029)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: MARLIN: Masked Autoencoder for facial video Representation LearnINg. https://app.cochat.ai/papers/10.1109/cvpr52729.2023.00150
The paper
Cai, Z., Ghosh, S., Stefanov, K., Dhall, A., Cai, J., Rezatofighi, H., Haffari, R., & Hayat, M. (2023). MARLIN: Masked Autoencoder for facial video Representation LearnINg. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr52729.2023.00150

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.