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

Learning modality knowledge with proxy for RGB-Infrared object detection

delete2026-02-03
delete0
PRE
AI
Y
You Ma
L
Lin Chai *
S
Shihan Mao
Y
Yucheng Zhang
DOI：10.1016/j.patcog.2026.113227delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• A novel RGB-Infrared object detection method is proposed. • Proxy tokens are employed for cross-modality feature interaction. • The mixture of knowledge decoupled experts achieves dual-modality feature fusion. • Demonstrate the superiority of the proposed method on 4 datasets.
Keywords:
RGB-Infrared object detection
proxy tokens
cross-modality feature interaction
knowledge decoupled experts
dual-modality feature fusion

Journal

Pattern Recognition cover
Pattern Recognition
IF:
7.6
Papers:
1.3W
Citations:
4.5W

Organization

No organization information available