# MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition

arXiv: https://arxiv.org/abs/2307.02227 · HTML: https://mlsanity.com/paper/2307.02227/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 73 references that are in the map.
- First posted on arXiv 5 Jul 2023.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [Masked Autoencoders that Listen](https://mlsanity.com/paper/2207.06405/) (2022)
- [Deep Facial Expression Recognition: A Survey](https://mlsanity.com/paper/1804.08348/) (2018)
- [TDN: Temporal Difference Networks for Efficient Action Recognition](https://mlsanity.com/paper/2012.10071/) (2020)
- [DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wild](https://mlsanity.com/paper/2008.05924/) (2020)
- [FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2203.09463/) (2022)
- [MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2208.00847/) (2022)
- [A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond](https://mlsanity.com/paper/2208.00173/) (2022)
- [Frame attention networks for facial expression recognition in videos](https://mlsanity.com/paper/1907.00193/) (2019)
- [MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens](https://mlsanity.com/paper/2105.15168/) (2021)
- [Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2208.10335/) (2022)
- [Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimation](https://mlsanity.com/paper/1906.06196/) (2019)
- [Exploiting multi-CNN features in CNN-RNN based Dimensional Emotion Recognition on the OMG in-the-wild Dataset](https://mlsanity.com/paper/1910.01417/) (2019)
- [Expression Snippet Transformer for Robust Video-based Facial Expression Recognition](https://mlsanity.com/paper/2109.08409/) (2021)

## Built on by (most cited first, 30 of 43)

- [Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning](https://mlsanity.com/paper/2406.11161/) (2024)
- [HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding](https://mlsanity.com/paper/2501.15111/) (2025)
- [From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2312.05447/) (2023)
- [GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition](https://mlsanity.com/paper/2312.04293/) (2023)
- [HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition](https://mlsanity.com/paper/2401.05698/) (2024)
- [FineCLIPER: Multi-modal Fine-grained CLIP for Dynamic Facial Expression Recognition with AdaptERs](https://mlsanity.com/paper/2407.02157/) (2024)
- [MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wild](https://mlsanity.com/paper/2404.09010/) (2024)
- [Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning](https://mlsanity.com/paper/2504.07198/) (2025)
- [Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data](https://mlsanity.com/paper/2409.06154/) (2024)
- [FaVChat: Hierarchical Prompt-Query Guided Facial Video Understanding with Data-Efficient GRPO](https://mlsanity.com/paper/2503.09158/) (2025)
- [All rivers run into the sea: Unified Modality Brain-like Emotional Central Mechanism](https://mlsanity.com/paper/2407.15590/) (2024)
- [Facial Expression Analysis and Its Potentials in IoT Systems: A Contemporary Survey](https://mlsanity.com/paper/2412.17616/) (2024)
- [VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection](https://mlsanity.com/paper/2505.02331/) (2025)
- [FE-Adapter: Adapting Image-based Emotion Classifiers to Videos](https://mlsanity.com/paper/2408.02421/) (2024)
- [MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition](https://mlsanity.com/paper/2404.18327/) (2024)
- [Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction](https://mlsanity.com/paper/2412.18748/) (2024)
- [PE-CLIP: A Parameter-Efficient Fine-Tuning of Vision Language Models for Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2503.16945/) (2025)
- [Action Unit Enhance Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2507.07678/) (2025)
- [Multimodal Large Language Models for End-to-End Affective Computing: Benchmarking and Boosting with Generative Knowledge Prompting](https://mlsanity.com/paper/2508.02429/) (2025)
- [Learn from Balance: Rectifying Knowledge Transfer for Long-Tailed Scenarios](https://mlsanity.com/paper/2409.07694/) (2024)
- [eMotions: A Large-Scale Dataset and Audio-Visual Fusion Network for Emotion Analysis in Short-form Videos](https://mlsanity.com/paper/2508.06902/) (2025)
- [Not all Blends are Equal: The BLEMORE Dataset of Blended Emotion Expressions with Relative Salience Annotations](https://mlsanity.com/paper/2601.13225/) (2026)
- [Audio-Visual Compound Expression Recognition Method based on Late Modality Fusion and Rule-based Decision](https://mlsanity.com/paper/2403.12687/) (2024)
- [Smile upon the Face but Sadness in the Eyes: Emotion Recognition based on Facial Expressions and Eye Behaviors](https://mlsanity.com/paper/2411.05879/) (2024)
- [MTCAE-DFER: Multi-Task Cascaded Autoencoder for Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2412.18988/) (2024)
- [Enhancing Ambiguous Dynamic Facial Expression Recognition with Soft Label-based Data Augmentation](https://mlsanity.com/paper/2506.20867/) (2025)
- [SyncLipMAE: Contrastive Masked Pretraining for Audio-Visual Talking-Face Representation](https://mlsanity.com/paper/2510.10069/) (2025)
- [Why Do Vision Language Models Struggle To Recognize Human Emotions?](https://mlsanity.com/paper/2604.15280/) (2026)
- [Soften the Mask: Adaptive Temporal Soft Mask for Efficient Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2502.21004/) (2025)
- [MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation](https://mlsanity.com/paper/2503.11026/) (2025)

## Abstract (arXiv)

Dynamic facial expression recognition (DFER) is essential to the development of intelligent and empathetic machines. Prior efforts in this field mainly fall into supervised learning paradigm, which is severely restricted by the limited labeled data in existing datasets. Inspired by recent unprecedented success of masked autoencoders (e.g., VideoMAE), this paper proposes MAE-DFER, a novel self-supervised method which leverages large-scale self-supervised pre-training on abundant unlabeled data to largely advance the development of DFER. Since the vanilla Vision Transformer (ViT) employed in VideoMAE requires substantial computation during fine-tuning, MAE-DFER develops an efficient local-global interaction Transformer (LGI-Former) as the encoder. Moreover, in addition to the standalone appearance content reconstruction in VideoMAE, MAE-DFER also introduces explicit temporal facial motion modeling to encourage LGI-Former to excavate both static appearance and dynamic motion information. Extensive experiments on six datasets show that MAE-DFER consistently outperforms state-of-the-art supervised methods by significant margins (e.g., +6.30% UAR on DFEW and +8.34% UAR on MAFW), verifying that it can learn powerful dynamic facial representations via large-scale self-supervised pre-training. Besides, it has comparable or even better performance than VideoMAE, while largely reducing the computational cost (about 38% FLOPs). We believe MAE-DFER has paved a new way for the advancement of DFER and can inspire more relevant research in this field and even other related tasks. Codes and models are publicly available at https://github.com/sunlicai/MAE-DFER.