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

DPTrack: Dual-prompt guided network for visual object tracking

delete2025-07-09
delete0
PRE
AI
K
Kang Liu
L
Long Liu
J
Jiaqi Wang
P
Pingyan Hu
Y
Yunhe Wang
DOI：10.1016/j.eswa.2025.128974delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• We propose a DPTrack to learn rich spatio-temporal context information for robust tracking. • Designing IPN network to capture dynamic appearance changes between nearby frames and generate instantaneous prompt. • Proposing ST-CPN network to learn consistency knowledge from previous frames through a set of learnable prompts. • Introducing SPC mechanism to select key frames and build spatio-temporal pooling via prototype metrics.

Journal

Expert Systems with Applications cover
Expert Systems with Applications
IF:
7.5
Papers:
2.9W
Citations:
10.2W

Organization

No organization information available