logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Zero persistent-memory template optimization for UAV tracking

delete2026-03-20
delete0
PRE
AI
Q
Qian Lu
G
Guixi Liu *
H
Hanlin Huang
R
Ruke Xiong
吴
吴志宇 (Zhiyu Wu) *
Y
Yi Zhang
DOI：10.1016/j.asoc.2026.115095delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Introduces AITR2U for robust initial template enhancement without relying on historical templates. • Integrates FcaNet-Top8 to enhance feature discrimination in complex UAV scenes. • Employs boundary-sensitive loss to improve the localization accuracy. • Outperforms state-of-the-art methods across five challenging aerial tracking benchmarks.
Keywords:
AITR2U
FcaNet-Top8
boundary-sensitive loss
UAV tracking
template enhancement

Journal

Applied Soft Computing cover
Applied Soft Computing
IF:
6.6
Papers:
1.4W
Citations:
4.8W

Organization

X
Xian University of Posts and Telecommunications
Scholars:
113
Papers: 46
Citations: 0
X
Xinjiang University
Scholars:
1.4W
Papers: 8.7K
Citations: 1.1W
X
Xidian University
Scholars:
2.4W
Papers: 1.9W
Citations: 9.7K
researcher View more organizations