Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment

ECCV 2018  ·  Zhiwen Shao, Zhilei Liu, Jianfei Cai, Lizhuang Ma ·

Facial action unit (AU) detection and face alignment are two highly correlated tasks since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection. Most existing AU detection works often treat face alignment as a preprocessing and handle the two tasks independently. In this paper, we propose a novel end-to-end deep learning framework for joint AU detection and face alignment, which has not been explored before. In particular, multi-scale shared features are learned firstly, and high-level features of face alignment are fed into AU detection. Moreover, to extract precise local features, we propose an adaptive attention learning module to refine the attention map of each AU adaptively. Finally, the assembled local features are integrated with face alignment features and global features for AU detection. Experiments on BP4D and DISFA benchmarks demonstrate that our framework significantly outperforms the state-of-the-art methods for AU detection.

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Facial Action Unit Detection BP4D JAA-Net Average F1 60.0 # 6
Facial Action Unit Detection DISFA JAA-Net Average F1 56.0 # 4

Methods


No methods listed for this paper. Add relevant methods here