English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Facial action unit (AU) detection and face alignment are two highlycorrelated tasks, since facial landmarks can provide precise AU locations tofacilitate the extraction of meaningful local features for AU detection.However, most existing AU detection works handle the two tasks independently bytreating face alignment as a preprocessing, and often use landmarks topredefine a fixed region or attention for each AU. In this paper, we propose anovel end-to-end deep learning framework for joint AU detection and facealignment, which has not been explored before. In particular, multi-scaleshared feature is learned firstly, and high-level feature of face alignment isfed into AU detection. Moreover, to extract precise local features, we proposean adaptive attention learning module to refine the attention map of each AUadaptively. Finally, the assembled local features are integrated with facealignment feature and global feature for AU detection. Extensive experimentsdemonstrate that our framework (i) significantly outperforms thestate-of-the-art AU detection methods on the challenging BP4D, DISFA, GFT andBP4D+ benchmarks, (ii) can adaptively capture the irregular region of each AU,(iii) achieves competitive performance for face alignment, and (iv) also workswell under partial occlusions and non-frontal poses. The code for our method isavailable at https://github.com/ZhiwenShao/PyTorch-JAANet.

J$\hat{\text{A}}$A-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention