Facial Action Unit Recognition Based on Transfer Learning
This addresses facial analysis for applications like emotion detection, but it is incremental as it applies standard transfer learning techniques.
The paper tackles facial action unit recognition in the wild by proposing a transfer learning method, achieving results on the ABAW competition dataset.
Facial action unit recognition is an important task for facial analysis. Owing to the complex collection environment, facial action unit recognition in the wild is still challenging. The 3rd competition on affective behavior analysis in-the-wild (ABAW) has provided large amount of facial images with facial action unit annotations. In this paper, we introduce a facial action unit recognition method based on transfer learning. We first use available facial images with expression labels to train the feature extraction network. Then we fine-tune the network for facial action unit recognition.