SiamHAS: Siamese Tracker with Hierarchical Attention Strategy for Aerial Tracking

SiamHAS: Siamese Tracker with Hierarchical Attention Strategy for Aerial Tracking

For the Siamese network-based trackers utilizing modern deep feature extraction networks without taking full advantage of the different levels of features, tracking drift is prone to occur in aerial scenarios, such as target occlusion, scale variation, and low-resolution target tracking. Additionall...

Full description

Bibliographic Details
Main Authors: Faxue Liu, Jinghong Liu, Qiqi Chen, Xuan Wang, Chenglong Liu
Format: Article
Language:English
Published: MDPI AG 2023-04-01
Series:Micromachines
Subjects:
Siamese tracker
deep learning
hierarchical attention strategy
multi-level feature enhancement
Online Access:https://www.mdpi.com/2072-666X/14/4/893

Internet

https://www.mdpi.com/2072-666X/14/4/893

Similar Items