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

Despite the recent advances in deep neural networks, standard convolutionalkernels limit the applications of these networks to the Euclidean domain only.Considering the geodesic nature of the measurement of the earth's surface,remote sensing is one such area that can benefit from non-Euclidean andspherical domains. For this purpose, we propose a novel Graph Neural Networkarchitecture for spatial and spatio-temporal classification using satelliteimagery. We propose a hybrid attention method to learn the relative importanceof irregular neighbors in remote sensing data. Instead of classifying eachpixel, we propose a method based on Simple Linear Iterative Clustering (SLIC)image segmentation and Graph Attention GAT. The superpixels obtained from SLICbecome the nodes of our Graph Convolution Network (GCN). We then construct aregion adjacency graph (RAG) where each superpixel is connected to every otheradjacent superpixel in the image, enabling information to propagate globally.Finally, we propose a Spatially driven Attention Graph Neural Network (SAG-NN)to classify each RAG. We also propose an extension to our SAG-NN forspatio-temporal data. Unlike regular grids of pixels in images, superpixels areirregular in nature and cannot be used to create spatio-temporal graphs. Weintroduce temporal bias by combining unconnected RAGs from each image into onesupergraph. This is achieved by introducing block adjacency matrices resultingin novel Spatio-Temporal driven Attention Graph Neural Network with BlockAdjacency matrix (STAG-NN-BA). We evaluate our proposed methods on two remotesensing datasets namely Asia14 and C2D2. In comparison with both non-graph andgraph-based approaches our SAG-NN and STAG-NN-BA achieved superior accuracy onall the datasets while incurring less computation cost. The code and datasetwill be made public via our GitHub repository.

Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA)