Scientific Research Publishing

Research on Structural Damage Identification Method Based on Convolutional Neural Network ()

1 College of Finance and Commerce, Guangzhou Railway Polytechnic, Guangzhou, China. 2 School of Intelligent Construction and Civil Engineering, Zhongyuan University of Technology, Zhengzhou, China. 3 ...
IEEE

Contrastive Graph Convolution Network With Skip Connections for Few-Shot Hyperspectral Image Classification

Abstract: Graph convolution networks (GCNs) have achieved impressive results for few-shot hyperspectral image (HSI) classification. However, current methods focus on migrating labels from support ...
Frontiers

High-efficiency sparse convolution operator for event-based cameras

Event-based cameras are bio-inspired vision sensors that mimic the sparse and asynchronous activation of the animal retina, offering advantages such as low latency and low computational load in ...
IEEE

Graph Multi-Convolution and Attention Pooling for Graph Classification

Abstract: Many studies have achieved excellent performance in analyzing graph-structured data. However, learning graph-level representations for graph classification is still a challenging task.
GitHub

error in inference process (no valid convolution algorithms available in CuDNN)

error in inference process (no valid convolution algorithms available in CuDNN) #25 ...
Scientific Research Publishing

Simplified Inception Module Based Hadamard Attention Mechanism for Medical Image Classification ()

1 Department of Statistics, Guangzhou University, Guangzhou, China. 2 Department of Economics, Jinan University, Guangzhou, China. Medical image classification has played an important role in the ...