.png){kind=icon}
返回
Facial Action Unit Detection and Intensity Estimation From Self-Supervised Representation
.png){kind=icon}
OA
AI
DOI：10.1109/TAFFC.2024.3367015.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As a fine-grained and local expression behavior measurement, facial action unit (FAU) analysis (e.g., detection and intensity estimation) has been documented for its time-consuming, labor-intensive, and error-prone annotation. Thus a long-standing challenge of FAU analysis arises from the data scarcity of manual annotations, limiting the generalization ability of trained models to a large extent. Amounts of previous works have made efforts to alleviate this issue via semi/weakly supervised methods and extra auxiliary information. However, these methods still require domain knowledge and have not yet avoided the high dependency on data annotation. This article introduces a robust facial representation model MAE-Face for AU analysis. Using masked autoencoding as the self-supervised pre-training approach, MAE-Face first learns a high-capacity model from a feasible collection of face images without additional data annotations. Then after being fine-tuned on AU datasets, MAE-Face exhibits convincing performance for both AU detection and AU intensity estimation, achieving a new state-of-the-art on nearly all the evaluation results. Further investigation shows that MAE-Face achieves decent performance even when fine-tuned on only 1% of the AU training set, strongly proving its robustness and generalization performance. The pre-trained model is available at our GitHub repository.
Keyword:
Gold
Estimation
Image reconstruction
Annotations
Face recognition
Task analysis
Visualization
Facial action unit
facial expression recognition
facial representation model
self-supervised pre-training
期刊
IF:
9.8
论文数:
1.4K
被引数:
9.1K
机构
暂无机构信息
引用论文
.png){kind=icon}
分享收藏分享收藏
查看更多内容