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 in the wild is a challenging problem, dueto the unconstrained variability in facial appearances and the lack of accurateannotations. Most existing methods depend on either impractical labor-intensivelabeling or inaccurate pseudo labels. In this paper, we propose an end-to-endunconstrained facial AU detection framework based on domain adaptation, whichtransfers accurate AU labels from a constrained source domain to anunconstrained target domain by exploiting labels of AU-related faciallandmarks. Specifically, we map a source image with label and a target imagewithout label into a latent feature domain by combining source landmark-relatedfeature with target landmark-free feature. Due to the combination of sourceAU-related information and target AU-free information, the latent featuredomain with transferred source label can be learned by maximizing thetarget-domain AU detection performance. Moreover, we introduce a novel landmarkadversarial loss to disentangle the landmark-free feature from thelandmark-related feature by treating the adversarial learning as a multi-playerminimax game. Our framework can also be naturally extended for use withtarget-domain pseudo AU labels. Extensive experiments show that our methodsoundly outperforms lower-bounds and upper-bounds of the basic model, as wellas state-of-the-art approaches on the challenging in-the-wild benchmarks. Thecode is available at https://github.com/ZhiwenShao/ADLD.

Unconstrained Facial Action Unit Detection via Latent Feature Domain