MARLIN: Masked Autoencoder for facial video Representation LearnINg
Open accessThe DOI matches its Crossref record; 43 of the 43 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.
Integrity signals
Registry
Cites
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.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325 · cited 3×
“After success of BERT [26] based masking, the vision community has also explored different design choices of masked auto encoding such as pixel level masking [17, 37, 80], token level masking [29] and deep feature based masking [6, 77], using vision Transformers [44, 52].”
BackgroundMethodAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
Context Encoders: Feature Learning by Inpainting
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., & Efros, A. A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.278 · Cited by 5,691
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · cited 1×
“For images of natural scenes and objects, self-supervised learning approaches using self-distillation [14], contrastive-learning [18,19], solving pre-text tasks such as jigsaw puzzle [53], and more recently autoencoding [37,71] have even outperformed the supervised learning approaches.”
MethodSGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051
IEMOCAP: Interactive emotional dyadic motion capture database
Busso, C., Bulut, M., Lee, C.-C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., & Narayanan, S. S. (2008) · Language Resources and Evaluation · doi:10.1007/s10579-008-9076-6 · Cited by 3,869
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2017) · arXiv · doi:10.48550/arxiv.1711.11248 · Cited by 3,664 · cited 1×
“The results indicate that MARLIN performs favorably against the supervised SOTA methods [2, 8, 15, 21, 24, 32, 47, 59, 61, 72].”
MethodTransformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595
Self-citationTransformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2021) · arXiv · doi:10.48550/arxiv.2101.01169 · Cited by 3,594
Self-citationFaceForensics++: Learning to Detect Manipulated Facial Images
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Niessner, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00009 · Cited by 3,314 · cited 13×
“4, we compare the performance of video manipulation on FaceForensics++ [62] dataset and report results in terms of video-level accuracy(↑) and AUC(↑).”
BackgroundMethodInfluentialVGGFace2: A Dataset for Recognising Faces across Pose and Age
Cao, Q., Shen, L., Xie, W., Parkhi, O. M., & Zisserman, A. (2018) · 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) · doi:10.1109/fg.2018.00020 · Cited by 3,032
Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
Noroozi, M., & Favaro, P. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_5 · Cited by 2,775
VoxCeleb2: Deep Speaker Recognition
Chung, J. S., Nagrani, A., & Zisserman, A. (2018) · Interspeech 2018 · doi:10.21437/interspeech.2018-1929 · Cited by 2,256
Rich Models for Steganalysis of Digital Images
Fridrich, J., & Kodovsky, J. (2012) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2012.2190402 · Cited by 2,144 · cited 1×
“The results indicate that MARLIN performs favorably against the supervised SOTA methods [2, 8, 15, 21, 24, 32, 47, 59, 61, 72].”
MethodMS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition
Guo, Y., Zhang, L., Hu, Y., He, X., & Gao, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_6 · Cited by 2,122 · cited 7×
“Recently, we have witnessed significant progress in deep neural network models to solve facial analysis tasks such as Facial Attribute Recognition (FAR) [32, 81], Facial Expression Recognition (FER) [45], DeepFake Detection (DFD) [66], and Lip Synchronization (LS) [41].”
BackgroundInfluentialMesoNet: a Compact Facial Video Forgery Detection Network
Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018) · 2018 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2018.8630761 · Cited by 1,872
StarGAN v2: Diverse Image Synthesis for Multiple Domains
Choi, Y., Uh, Y., Yoo, J., & Ha, J.-W. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00821 · Cited by 1,663
Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph
Bagher Zadeh, A., Liang, P. P., Poria, S., Cambria, E., & Morency, L.-P. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1208 · Cited by 1,433 · cited 6×
“Following the prior works [7, 25], we use overall accuracy( ↑ ) as metrics.”
BackgroundMethodInfluentialMultiscale vision transformers
Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., & Feichtenhofer, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00675 · Cited by 1,407 · cited 1×
“MViT-v1 [30] and MViT-v2 [49]) and CNNs (i.”
Deepfakes and beyond: A Survey of face manipulation and fake detection
Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.06.014 · Cited by 1,237
Face X-Ray for More General Face Forgery Detection
Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., & Guo, B. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00505 · Cited by 1,211
Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues
Qian, Y., Yin, G., Sheng, L., Chen, Z., & Shao, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58610-2_6 · Cited by 1,058
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Tong, Z., Song, Y., Wang, J., & Wang, L. (2022) · arXiv · doi:10.48550/arxiv.2203.12602 · Cited by 909
A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild
Prajwal, K. R., Mukhopadhyay, R., Namboodiri, V. P., & Jawahar, C. V. (2020) · Proceedings of the 28th ACM International Conference on Multimedia · doi:10.1145/3394171.3413532 · Cited by 897
A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer
Bayar, B., & Stamm, M. C. (2016) · Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/2909827.2930786 · Cited by 838 · cited 1×
“The results indicate that MARLIN performs favorably against the supervised SOTA methods [2, 8, 14, 20, 23, 30, 44, 55, 57, 68].”
MethodMasked Feature Prediction for Self-Supervised Visual Pre-Training
Wei, C., Fan, H., Xie, S., Wu, C.-Y., Yuille, A., & Feichtenhofer, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01426 · Cited by 587
Intriguing Properties of Vision Transformers
Naseer, M., Ranasinghe, K., Khan, S., Hayat, M., Khan, F. S., & Yang, M.-H. (2021) · arXiv · doi:10.48550/arxiv.2105.10497 · Cited by 431 · cited 2×
“After success of BERT [26] based masking, the vision community has also explored different design choices of masked auto encoding such as pixel level masking [17, 37, 80], token level masking [29] and deep feature based masking [6, 77], using vision Transformers [44, 52].”
MethodSelf-citationThe Human Face as a Dynamic Tool for Social Communication
Jack, R. E., & Schyns, P. G. (2015) · Current Biology · doi:10.1016/j.cub.2015.05.052 · Cited by 405
M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection
Wang, J., Wu, Z., Ouyang, W., Han, X., Chen, J., Jiang, Y.-G., & Li, S.-N. (2022) · Proceedings of the 2022 International Conference on Multimedia Retrieval · doi:10.1145/3512527.3531415 · Cited by 368 · cited 1×
“Following prior literature [12, 58, 76], we use accuracy( ↑ ) and AUC( ↑ ) as the evaluation metrics.”
MethodCozzolino, D., Poggi, G., & Verdoliva, L. (2017) · Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/3082031.3083247 · Cited by 349 · cited 1×
“The results indicate that MARLIN performs favorably against the supervised SOTA methods [2, 8, 15, 21, 24, 32, 47, 59, 61, 72].”
MethodMasked Autoencoders As Spatiotemporal Learners
Feichtenhofer, C., Fan, H., Li, Y., & He, K. (2022) · arXiv · doi:10.48550/arxiv.2205.09113 · Cited by 345
StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2
Skorokhodov, I., Tulyakov, S., & Elhoseiny, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00361 · Cited by 199
You Said That?: Synthesising Talking Faces from Audio
Jamaludin, A., Chung, J. S., & Zisserman, A. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01150-y · Cited by 189
VideoGPT: Video Generation using VQ-VAE and Transformers
Yan, W., Zhang, Y., Abbeel, P., & Srinivas, A. (2021) · arXiv · doi:10.48550/arxiv.2104.10157 · Cited by 156 · cited 3×
“The adversarial adaptation considers the Wassenstain GAN loss [5] for better reconstruction of spatio-temporal facial patterns which in turn helps in learning rich representation.”
MethodCai, Z., Stefanov, K., Dhall, A., & Hayat, M. (2022) · 2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta56598.2022.10034605 · Cited by 99
Self-citationSpeech2Video: Cross-Modal Distillation for Speech to Video Generation
Si, S., Wang, J., Qu, X., Cheng, N., Wei, W., Zhu, X., & Xiao, J. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-1996 · Cited by 12
Research works printed but not linked: 45
- qiu, 0, Learning Spatio-Temporal Representation With Pseudo-3D Residual Net-works, Proceedings of the IEEE International Conference on Computer Vision, 5533
- paszke, 2019, PyTorch: An Imperative Style, High-Performance Deep Learning Library, Advances in neural information processing systems, 32
- bulat, 2022, Pre-training strategies and datasets for facial representation learning
- 10.5244/C.29.41 · DOI · Paper page
- chen, 0, Generative Pre-training From Pixels, Proceedings of the 37th International Conference on Machine Learning, 1691
- 10.1109/CVPR46437.2021.00574 · DOI · Paper page
- chen, 2020, Big Self-Supervised Models are Strong Semi-Supervised Learners, Advances in neural information processing systems, 33, 22243
- chen, 0, A Simple Framework for Contrastive Learning of Visual Representations, International Conference on Machine Learning, 1597
- 10.1109/ICCV.2015.425 · DOI · Paper page
- korshunov, 2018, DeepFakes: a New Threat to Face Recognition?, Assessment and Detection
- koromilas, 2022, Un-supervised Multimodal Language Representations using Convolutional Autoencoders
- 10.1109/TAFFC.2020.2981446 · DOI · Paper page
- prajwal, 2019, Towards Automatic Face-to-Face Translation, Proceedings of the 27th ACM International Conference on Multimedia MM '19, 1428
- zhuang, 0, Few-Shot Knowledge Trans-fer for Fine-Grained Cartoon Face Generation, 2021 IEEE International Conference on Multimedia and Expo (ICME), 1
- zhu, 2022, Celebv-hq A large-scale video facial attributes dataset
- 10.4108/eai.14-4-2021.169187 · DOI
- 10.1109/CVPR52688.2022.00476 · DOI · Paper page
- 10.1109/CVPR42600.2020.00615 · DOI
- 10.1007/s00521-019-04559-1 · DOI
- aneja, 2020, Generalized Zero and Few-Shot Transfer for Facial Forgery Detection
- baevski, 2022, data2vec: A General Frame-work for Self-supervised Learning in Speech, Language of Vision
- arjovsky, 0, Wasserstein Generative Adversarial Networks, Proceedings of the 34th International Conference on Machine Learning, 214
- yu, 0, Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks, International Conference on Learning Representations
- 10.1109/CVPR52688.2022.01814 · DOI · Paper page
- 10.1609/aaai.v32i1.12024 · DOI · Paper page
- 10.1109/CVPR52688.2022.00943 · DOI · Paper page
- hao, 2021, GANcraft Unsupervised 3D Neural Rendering of Minecraft Worlds
- wu, 0, ReenactGAN: Learning to Reenact Faces via Boundary Transfer, Proceedings of the European con-ference on computer vision (ECCV), 603
- 10.1109/CVPR.2011.5995566 · DOI · Paper page
- haugh, 2009, Face and Interaction, Face Communication and Social Interaction, 1
- 10.1145/3474085.3478324 · DOI · Paper page
- wang, 2022, Attention-Based Lip Audio-Visual Synthe-sis for Talking Face Generation in the Wild
- 10.1109/ICIP.2018.8451242 · DOI
- 10.3390/electronics9081188 · DOI · Paper page
- 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
- 10.1038/s41562-021-01097-6 · DOI · Paper page
- 10.18653/v1/2020.challengehml-1.1 · DOI
- sun, 2022, M$A3$Video Masked Motion Modeling for Self-Supervised Video Representation Learning
- chung, 2017, Lip reading in profile, 2017 British Machine Vision Conference
- 10.1109/CVPR.2017.195 · DOI · Paper page
- 10.1109/CVPR46437.2021.01174 · DOI
- donahue, 2019, Large Scale Adversar-ial Representation Learning, Advances in Neural Infor-Mation Processing Systems, 32
- el-nouby, 2021, Are large-scale datasets necessary for self-supervised pre-training?
- radford, 2016, Unsu-pervised Representation Learning with Deep Convolutional Generative Adversarial Networks, 4th International Con-ference on Learning Representations ICLR 2016
- 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
NGUYEN, D., MEJRI, N., SINGH, I. P., KULESHOVA, P., ASTRID, M., KACEM, A., GHORBEL, E., & AOUADA, D. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01647 · Cited by 93
Cai, Z., Ghosh, S., Dhall, A., Gedeon, T., Stefanov, K., & Hayat, M. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103818 · Cited by 63
Self-citationAV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
Cai, Z., Ghosh, S., Adatia, A. P., Hayat, M., Dhall, A., Gedeon, T., & Stefanov, K. (2024) · Proceedings of the 32nd ACM International Conference on Multimedia · doi:10.1145/3664647.3680795 · Cited by 59
“For the segment-based meth-ods MDS [13] and MARLIN [6], we used a sliding window to sample segments from the video for training and inference.”
Self-citationAV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset
Cai, Z., Ghosh, S., Adatia, A. P., Hayat, M., Dhall, A., Gedeon, T., & Stefanov, K. (2023) · arXiv · doi:10.48550/arxiv.2311.15308 · Cited by 59
Self-citationContext-aware Alignment and Mutual Masking for 3D-Language Pre-training
Jin, Z., Hayat, M., Yang, Y., Guo, Y., & Lei, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01057 · Cited by 56
“Further, conditional MLM [10,28] and masked multi-modal modeling [7, 14, 16, 26, 42, 62] have developed masking based reconstruction schemes to learn multi-modal features in VLP.”
Self-citation
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
- 43
- 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
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.