Knowledge Commons of Institute of Automation,CAS
MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition | |
Licai Sun1,2![]() ![]() ![]() ![]() | |
2023 | |
会议名称 | ACM Multimedia |
会议日期 | October 29-November 3, 2023 |
会议地点 | Ottawa, ON, Canada |
摘要 | 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 selfsupervised method which leverages large-scale self-supervised pretraining 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, MAEDFER 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. |
七大方向——子方向分类 | 智能交互 |
国重实验室规划方向分类 | 人机混合智能 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57087 |
专题 | 多模态人工智能系统全国重点实验室 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Department of Automation, Tsinghua University 4.Beijing National Research Center for Information Science and Technology, Tsinghua University |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Licai Sun,Zheng Lian,Bin Liu,et al. MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition[C],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
3581783.3612365.pdf(1960KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论