Multi-Head Self-Attention for 3D Point Cloud Classification

Multi-Head Self-Attention for 3D Point Cloud Classification

3D point cloud classification is a hot issue in recent years. 3D point cloud is different from regular data such as image and text. Disorder of point cloud makes two-dimensional (2D) convolution neural network (CNN) hard to be applied. When features are acquired from input data, it is important to e...

Full description

Bibliographic Details
Main Authors: Xue-Yao Gao, Yan-Zhao Wang, Chun-Xiang Zhang, Jia-Qi Lu
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
INDEX TERMS point cloud
convolutional neural network
self-attention mechanism
feature vector
spatial coordinates
shape descriptor
Online Access:https://ieeexplore.ieee.org/document/9319138/

Internet

https://ieeexplore.ieee.org/document/9319138/

Similar Items