Separable Self-Attention Mechanism for Point Cloud Local and Global Feature Modeling

Separable Self-Attention Mechanism for Point Cloud Local and Global Feature Modeling

The self-attention mechanism has an excellent ability to capture long-range dependencies of data. To enable the self-attention mechanism in point cloud tasks to focus on both local and global contexts, we design a separable self-attention mechanism for point clouds by decomposing the construction of...

Full description

Bibliographic Details
Main Authors: Fan Wang, Xiaoli Wang, Dan Lv, Lumei Zhou, Gang Shi
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Point cloud
3D deep learning
self-attention
classification
part segmentation
Online Access:https://ieeexplore.ieee.org/document/9978621/

Internet

https://ieeexplore.ieee.org/document/9978621/

Similar Items