Skip to content

594422814/MCCT

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Multi-Cue Correlation Tracker

Code for tracker in the paper Multi-Cue Correlation Filters for Robust Visual Tracking, by Ning Wang, Wengang Zhou et. al - to appear in CVPR 2018.

In this work, we propose to utilize multiple weak experts for online tracking. Our efficient framework achieves state-of-the-art performance just using standard DCFs !

Contacts

For questions about the code or paper, please feel free to contact me: wn6149@mail.ustc.edu.cn

Citing

If you find MCCT useful in your research, please consider citing:

@InProceedings{NingCVPR2018,  
	Title                    = {Multi-Cue Correlation Filters for Robust Visual Tracking},  
	Author                   = {Ning Wang, Wengang Zhou, Qi Tian, Richang Hong, Meng Wang, Houqiang Li},  
	Booktitle                = {CVPR},  
	Year                     = {2018}  
}

Prerequisites

For the MCCT-H (Hand-crafted features only) tracker, just start Matlab and run the runTracker.m. To run the MCCT tracker with deep features, please download the VGG-19 and compile the Matconvnet following the description in README (in MCCT/model/).

Acknowledgments

Some codes of this work are adopted from previous trackers (Staple, HCF).

  • L. Bertinetto, J. Valmadre, S. Golodetz, O. Miksik, and P. Torr. Staple: Complementary learners for real-time tracking. In CVPR, 2016.
  • C. Ma, J.-B. Huang, X. Yang, and M.-H. Yang. Hierarchical convolutional features for visual tracking. In ICCV, 2015.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published