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.

翻译：动态面部表情识别（DFER）对于发展智能且具有共情能力的机器至关重要。该领域的先前研究主要采用监督学习范式，然而现有数据集中有限的标注数据严重制约了其发展。受掩码自编码器（如VideoMAE）近期取得的空前成功启发，本文提出MAE-DFER——一种新颖的自监督方法，通过在海量无标注数据上进行大规模自监督预训练，显著推动了DFER领域的发展。由于VideoMAE中采用的原始视觉Transformer（ViT）在微调阶段需消耗大量计算资源，MAE-DFER开发了一种高效局部-全局交互Transformer（LGI-Former）作为编码器。此外，除了VideoMAE中独立的表观内容重建任务，MAE-DFER还引入了显式的时间域面部运动建模，促使LGI-Former同时挖掘静态表观与动态运动信息。在六个数据集上的大量实验表明，MAE-DFER始终以显著优势超越最先进的监督方法（例如在DFEW上UAR提升+6.30%，在MAFW上UAR提升+8.34%），验证了其通过大规模自监督预训练学习强大动态面部表征的能力。同时，与VideoMAE相比，MAE-DFER在达到相当甚至更优性能的前提下，大幅降低了计算成本（约减少38%的FLOPs）。我们相信MAE-DFER为DFER的发展开辟了新路径，并能启发该领域乃至其他相关任务的更多研究。代码与模型已开源至https://github.com/sunlicai/MAE-DFER。