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 has been researched for decades with promisingfruits. 3D human pose lifting is one of the promising research directionstoward the task where both estimated pose and ground truth pose data are usedfor training. Existing pose lifting works mainly focus on improving theperformance of estimated pose, but they usually underperform when testing onthe ground truth pose data. We observe that the performance of the estimatedpose can be easily improved by preparing good quality 2D pose, such asfine-tuning the 2D pose or using advanced 2D pose detectors. As such, weconcentrate on improving the 3D human pose lifting via ground truth data forthe future improvement of more quality estimated pose data. Towards this goal,a simple yet effective model called Global-local Adaptive Graph ConvolutionalNetwork (GLA-GCN) is proposed in this work. Our GLA-GCN globally models thespatiotemporal structure via a graph representation and backtraces local jointfeatures for 3D human pose estimation via individually connected layers. Tovalidate our model design, we conduct extensive experiments on three benchmarkdatasets: Human3.6M, HumanEva-I, and MPI-INF-3DHP. Experimental results showthat our GLA-GCN implemented with ground truth 2D poses significantlyoutperforms state-of-the-art methods (e.g., up to around 3%, 17%, and 14% errorreductions on Human3.6M, HumanEva-I, and MPI-INF-3DHP, respectively). GitHub:https://github.com/bruceyo/GLA-GCN.

GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video