Large-scale language models show promising text generation capabilities, but users cannot easily control particular aspects of the generated text.
Graph Convolutional Networks (GCNs) are a novel and powerful method for dealing with non-Euclidean data, while Convolutional Neural Networks (CNNs) can learn features from Euclidean data such as images.
Pulmonary Artery–Vein Classification
3D MEDICAL IMAGING SEGMENTATION
PULMONARY ARTERY–VEIN CLASSIFICATION