Hierarchical Graph Attention Based Multi-View Convolutional Neural Network for 3D Object Recognition

Hierarchical Graph Attention Based Multi-View Convolutional Neural Network for 3D Object Recognition

For multi-view convolutional neural network based 3D object recognition, how to fuse the information of multiple views is a key factor affecting the recognition performance. Most traditional methods use max-pooling algorithm to obtain the final 3D object feature, which does not take into account the...

Full description

Bibliographic Details
Main Authors: Hui Zeng, Tianmeng Zhao, Ruting Cheng, Fuzhou Wang, Jiwei Liu
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
3D object recognition
multi-view convolutional neural network
graph attention network
feature aggregation
Online Access:https://ieeexplore.ieee.org/document/9355182/

Internet

https://ieeexplore.ieee.org/document/9355182/

Similar Items