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...
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: | |
Online Access: | https://ieeexplore.ieee.org/document/9319138/ |
Similar Items
-
A Local Feature Descriptor Based on Rotational Volume for Pairwise Registration of Point Clouds
by: Xiong Fengguang, et al.
Published: (2020-01-01) -
MPAN: Multi-Part Attention Network for Point Cloud Based 3D Shape Retrieval
by: Zirui Li, et al.
Published: (2020-01-01) -
Orientation-Encoding CNN for Point Cloud Classification and Segmentation
by: Hongbin Lin, et al.
Published: (2021-08-01) -
Self-Supervised Point Set Local Descriptors for Point Cloud Registration
by: Yijun Yuan, et al.
Published: (2021-01-01) -
Multi-Head Attentional Point Cloud Classification and Segmentation Using Strictly Rotation-Invariant Representations
by: Zhiyong Tao, et al.
Published: (2021-01-01)