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/

Zendy Plus

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

Zendy Tools

Zendy Open

Facial pose estimation refers to the task of predicting face orientation froma single RGB image. It is an important research topic with a wide range ofapplications in computer vision. Label distribution learning (LDL) basedmethods have been recently proposed for facial pose estimation, which achievepromising results. However, there are two major issues in existing LDL methods.First, the expectations of label distributions are biased, leading to a biasedpose estimation. Second, fixed distribution parameters are applied for alllearning samples, severely limiting the model capability. In this paper, wepropose an Anisotropic Spherical Gaussian (ASG)-based LDL approach for facialpose estimation. In particular, our approach adopts the spherical Gaussiandistribution on a unit sphere which constantly generates unbiased expectation.Meanwhile, we introduce a new loss function that allows the network to learnthe distribution parameter for each learning sample flexibly. Extensiveexperimental results show that our method sets new state-of-the-art records onAFLW2000 and BIWI datasets.

Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian