GSAP: A Global Structure Attention Pooling Method for Graph-Based Visual Place Recognition
The Visual Place Recognition problem aims to use an image to recognize the location that has been visited before. In most of the scenes revisited, the appearance and view are drastically different. Most previous works focus on the 2-D image-based deep learning method. However, the convolutional feat...
Main Authors: | Yukun Yang, Bo Ma, Xiangdong Liu, Liang Zhao, Shoudong Huang |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/8/1467 |
Similar Items
-
Uniform Pooling for Graph Networks
by: Jian Qin, et al.
Published: (2020-09-01) -
Hierarchical Pooling in Graph Neural Networks to Enhance Classification Performance in Large Datasets
by: Hai Van Pham, et al.
Published: (2021-09-01) -
Co-Attention Graph Pooling for Efficient Pairwise Graph Interaction Learning
by: Junhyun Lee, et al.
Published: (2023-01-01) -
Scene graph descriptors for visual place classification from noisy scene data
by: Tomoya Ohta, et al.
Published: (2023-12-01) -
A Graph Database Model for Knowledge Extracted from Place Descriptions
by: Hao Chen, et al.
Published: (2018-06-01)