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 hand pose estimation from RGB images suffers from the difficulty ofobtaining the depth information. Therefore, a great deal of attention has beenspent on estimating 3D hand pose from 2D hand joints. In this paper, weleverage the advantage of spatial-temporal Graph Convolutional Neural Networksand propose LG-Hand, a powerful method for 3D hand pose estimation. Our methodincorporates both spatial and temporal dependencies into a single process. Weargue that kinematic information plays an important role, contributing to theperformance of 3D hand pose estimation. We thereby introduce two new objectivefunctions, Angle and Direction loss, to take the hand structure into account.While Angle loss covers locally kinematic information, Direction loss handlesglobally kinematic one. Our LG-Hand achieves promising results on theFirst-Person Hand Action Benchmark (FPHAB) dataset. We also perform an ablationstudy to show the efficacy of the two proposed objective functions.

LG-Hand: Advancing 3D Hand Pose Estimation with Locally and Globally Kinematic Knowledge