Adaptive attention graph convolution network with normalized embedded Gaussian for rapid serial visualization presentation decoding

Mengyuan Zhao

doi:10.1016/j.engappai.2025.112093

Adaptive attention graph convolution network with normalized embedded Gaussian for rapid serial visualization presentation decoding

2025-08-28

0

PRE

AI

DOI：10.1016/j.engappai.2025.112093

Original

Save

Abstract

En 中文

• The Gaussian-AAGCN is proposed, multi-subgraph convolution is designed to extract more complementary features. • An adaptive adjacency matrix is proposed to learn topological relationships of brain regions, avoiding information loss. • CBAM is integrated to adaptive feature refinement, enhancing important spatiotemporal features weights. • Compared with other advanced models, the proposed model achieves superior performance.

Keywords:

Gaussian-AAGCN

multi-subgraph convolution

adaptive adjacency matrix

CBAM

spatiotemporal feature refinement

Adaptive attention graph convolution network with normalized embedded Gaussian for rapid serial visualization presentation decoding

Abstract

Journal

Organization

Cited Papers