Wavelet-domain feature decoupling for weakly supervised multi-object tracking  

作　　者：Yu-Lei LI Yan YAN Yang LU Hanzi WANG 

机构地区：[1]Fujian Key Laboratory of Sensing and Computing for Smart City,School of Informatics,XiamenUniversity,Xiamen361005,China

出　　处：《Science China(Information Sciences)》2024年第8期335-336,共2页中国科学（信息科学）（英文版）

基　　金：supported by National Natural Science Foundation of China(Grant Nos.U21A20514,62002302);FuXiaQuan National Independent Innovation Demonstration Zone Collaborative Innovation Platform Project(GrantNo.3502ZCQXT2022008).

摘　　要：Multi-object tracking(MOT)aims to discover interesting foreground targets and meanwhile generate robust trajectories of these targets with different data association algorithms based on identity embedding features(Re-ID features)[1]or motion cues[2].During the past few decades,some advanced MOT methods have achieved considerable progress due to their wide range of applications in modern autonomous driving and intelligent video analysis.

关 键 词：ANALYSIS WEAKLY AUTONOMOUS 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]