IEEE

Dual-Semantic Graph Convolution Network for Hyperspectral Image Classification With Few Labeled Samples

Abstract: In recent years, superpixel-based graph convolutional networks (GCNs) have drawn increasing attention within the hyperspectral image (HSI) classification community. Due to the ...
IEEE

Global and Local Graph Convolution Network for Multi-Label Class Incremental Learning

Abstract: Despite significant progresses in single-label class incremental learning (CIL), its multi-label counterpart remains relatively understudied which is called multi-label class incremental ...
C&EN

Generating High-Temperature Polymer Dielectrics with a Graph Convolution and Reinforcement Learning Framework

State Key Laboratory of Power System Operation and Control, Department of Electrical Engineering, Tsinghua University, Beijing 100084, People’s Republic of China ...