EurekAlert!

PolyU develops novel AI graph neural network models to unravel interdisciplinary complexities in image recognition and neuroscience

As an emerging technology in the field of artificial intelligence (AI), graph neural networks (GNNs) are deep learning models designed to process graph-structured data. Currently, GNNs are effective ...
GitHub

[ICLR 2026] VeloxSeg: Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation

Overview of VeloxSeg. VeloxSeg employs an encoder-decoder architecture with Paired Window Attention (PWA) and Johnson-Lindenstrauss lemma-guided convolution (JLC) on the left, using 1x1 convolution as ...
IEEE

TGMN: Two-Stage Graph Convolutional Mamba Network for Hyperspectral Image Classification

Abstract: Local spectral features and global spatial context are essential for hyperspectral image (HSI) classification. However, existing methods based on convolutional neural networks (CNNs), graph ...
C&EN

A Graph Neural Network Charge Model Targeting Accurate Electrostatic Properties of Organic Molecules

School of Natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne NE1 7RU, U.K. Kuano, Hauxton House, Mill Scitech Park, Mill Lane, Cambridge, England CB22 5HX, U.K. Department ...
Frontiers

A multi-domain graph convolutional network-based prediction model for personalized motor imagery action

Brain-computer interfaces (BCIs) are advanced and innovative systems that enable direct communication between humans and external devices by utilizing data encoded in the brain activity (Shi et al., ...
IEEE

BGC-Net: Bilateral Graph Convolutional Network for Weakly-supervised Semantic Segmentation of Large-scale Point Clouds

Abstract: Weakly-supervised point cloud semantic segmentation (WS-PCS) has attracted increasing attention due to the challenge of sparse annotations. A central problem is how to effectively extract ...