AGSF: Adaptive Graph Formulation and Hand-Crafted Graph Spectral Features for Shape Representation
Addressing intra-class variation in high similarity shapes is a challenging task in shape representation due to highly common local and global shape characteristics. Therefore, this paper proposes a new set of hand-crafted features for shape recognition by exploiting spectral features of the underly...
Main Authors: | Basheer Alwaely, Charith Abhayaratne |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9212360/ |
Similar Items
-
Graph Spectral Domain Feature Learning With Application to in-Air Hand-Drawn Number and Shape Recognition
by: Basheer Alwaely, et al.
Published: (2019-01-01) -
Blind Mesh Assessment Based on Graph Spectral Entropy and Spatial Features
by: Yaoyao Lin, et al.
Published: (2020-02-01) -
Some properties of eccentrical graphs
by: Zikai Tang
Published: (2024-02-01) -
Scalable Graph Convolutional Networks With Fast Localized Spectral Filter for Directed Graphs
by: Chensheng Li, et al.
Published: (2020-01-01) -
Line graph contrastive learning for node classification
by: Mingyuan Li, et al.
Published: (2024-04-01)