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

3D human pose estimation is still a challenging problem despite the largeamount of work that has been done in this field. Generally, most methodsdirectly use neural networks and ignore certain constraints (e.g., reprojectionconstraints and joint angle and bone length constraints). This paper proposes aweakly supervised GAN-based model for 3D human pose estimation that considers3D information along with 2D information simultaneously, in which areprojection network is employed to learn the mapping of the distribution from3D poses to 2D poses. In particular, we train the reprojection network and thegenerative adversarial network synchronously. Furthermore, inspired by thetypical kinematic chain space (KCS) matrix, we propose a weighted KCS matrix,which is added into the discriminator's input to impose joint angle and bonelength constraints. The experimental results on Human3.6M show that our methodoutperforms state-of-the-art methods by approximately 24.7\%.

A Synchronized Reprojection-based Model for 3D Human Pose Estimation