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

Graph Neural Networks (GNNs) generalize neural networks from applications onregular structures to applications on arbitrary graphs, and have shown successin many application domains such as computer vision, social networks andchemistry. In this paper, we extend GNNs along two directions: a) allowingfeatures at each node to be represented by 2D spatial confidence maps insteadof 1D vectors; and b) proposing an efficient operation to integrate informationfrom neighboring nodes through 2D convolutions with different learnable kernelsat each edge. The proposed SIA-GCN can efficiently extract spatial informationfrom 2D maps at each node and propagate them through graph convolution. Byassociating each edge with a designated convolution kernel, the SIA-GCN couldcapture different spatial relationships for different pairs of neighboringnodes. We demonstrate the utility of SIA-GCN on the task of estimating handkeypoints from single-frame images, where the nodes represent the 2D coordinateheatmaps of keypoints and the edges denote the kinetic relationships betweenkeypoints. Experiments on multiple datasets show that SIA-GCN provides aflexible and yet powerful framework to account for structural constraintsbetween keypoints, and can achieve state-of-the-art performance on the task ofhand pose estimation.

SIA-GCN: A Spatial Information Aware Graph Neural Network with 2D Convolutions for Hand Pose Estimation