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

RAP-SORT: Advanced Multi-Object Tracking for complex scenarios

delete2026-01-21
delete0
PRE
AI
S
Shuming Zhang
Y
Yuhang Zhu
Y
Y. Y. Sun
W
Weiyong Liu
Z
Zhangjin Huang *
DOI：10.1016/j.displa.2026.103361delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• RAP-SORT extends SORT with four new modules: RTCM, AOCR, PDIoU, and WD. • Our approach integrates strong and weak cues while preserving real-time online tracking. • RAP-SORT achieves state-of-the-art HOTA on DanceTrack (66.7) and MOT20 (64.2).

Journal

Displays cover
Displays
IF:
3.4
Papers:
2.2K
Citations:
3.2K

Organization

U
university of science and technology of china
Scholars:
1.0W
Papers: 3.9K
Citations: 3