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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate estimation of three-dimensional human skeletons from depth imagescan provide important metrics for healthcare applications, especially forbiomechanical gait analysis. However, there exist inherent problems associatedwith depth images captured from a single view. The collected data is greatlyaffected by occlusions where only partial surface data can be recorded.Furthermore, depth images of human body exhibit heterogeneous characteristicswith viewpoint changes, and the estimated poses under local coordinate systemsare expected to go through equivariant rotations. Most existing pose estimationmodels are sensitive to both issues. To address this, we propose a novelapproach for cross-view generalization with an occlusion-invariantsemi-supervised learning framework built upon a novel rotation-equivariantbackbone. Our model was trained with real-world data from a single view andunlabelled synthetic data from multiple views. It can generalize well on thereal-world data from all the other unseen views. Our approach has shownsuperior performance on gait analysis on our ICL-Gait dataset compared to otherstate-of-the-arts and it can produce more convincing keypoints on ITOP dataset,than its provided "ground truth".

Occlusion-Invariant Rotation-Equivariant Semi-Supervised Depth Based Cross-View Gait Pose Estimation