Home

Awesome

LTMU

LTMU figure

Introduction

Our Meta-updater can be easily embedded into other online-update algorithms(Dimp, ATOM, ECO, RT-MDNet...) to make their online-update more accurately in long-term tracking task. More info.

Experiments

+MU = Basetracker+Meta-Updater

+LTMU = Basetracker+Meta-Updater+Global Detection+Verifier+Bbox refine

TrackerLaSOT(AUC)VOT2020 LT(F)VOT2018 LT(F)TLP(AUC)Link
RT-MDNet0.3350.3380.3670.276Paper/Code/Results
RT-MDNet+MU0.3540.3960.4070.337Paper/Code/Results
ATOM0.5110.4970.5100.399Paper/Code/Results
ATOM+MU0.5410.6200.6280.473Paper/Code/Results
DiMP0.5780.5730.5870.514Paper/Code/Results
DiMP+MU0.6020.6410.6490.564Paper/Code/Results
DiMP+LTMU0.6050.691-0.572Paper/Code/Results
PrDiMP0.6120.6320.6310.535Paper/Code/Results
PrDiMP+MU0.6150.6610.6750.582Paper/Code/Results
SuperDiMP0.6460.6470.6670.552Paper/Code/Results
SuperDiMP+MU0.6580.7040.7070.595Paper/Code/Results
D3S0.4940.4370.4450.390Paper/Code/Results
D3S+MU0.5200.5180.5340.413Paper/Code/Results
ECO----Paper/Code/Results
ECO+MU----Paper/Code/Results
MDNet----Paper/Code/Results
MDNet+MU----Paper/Code/Results

Paper link

Citation

Please cite the above publication if you use the code or compare with the LTMU tracker in your work. Bibtex entry:

@inproceedings{Dai_2020_CVPR,
author = {Kenan Dai, Yunhua Zhang, Dong Wang, Jianhua Li, Huchuan Lu, Xiaoyun Yang},
title = {{High-Performance Long-Term Tracking with Meta-Updater},
booktitle = {CVPR},
year = {2020}
}

Results

LTMU