arrow
Return

Boundary-aware shape recognition using dynamic graph convolutional networks

delete2025-09-29
delete0
PRE
AI
J
Jinming Zhao
J
Junyu Dong
H
Huiyu Zhou
X
Xinghui Dong
DOI:10.1016/j.patcog.2025.112511delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Making the first effort on applying Graph Convolutional Networks (GCNs) to 2D shape recognition. • Proposing a Boundary-Aware Shape Recognition Graph Convolutional Network (BASR-GCN) which integrates both the boundary and skeleton cues. • Introducing a multi-scale BASR-GCN to extract shape features at different scales.

Journal

Pattern Recognition cover
Pattern Recognition
IF:
7.6
Papers:
1.3W
Citations:
4.5W

Organization

O
ocean university of china
Scholars:
3.1W
Papers: 2.0W
Citations: 21
U
university of leicester
Scholars:
2.0W
Papers: 1.7W
Citations: 25