Target-Aware Deep Tracking

Matlab implementation of the Target-Aware Deep Tracking (TADT) method.

Installation

This code has been tested on a Ubantu Platform with Matlab and the MatConvNet toolbox. You may install it with the following steps:

1. Clone the GIT repository:
   $ git clone
2. Start Matlab and navigate to the repository
3. Compile the MatConvNet toolkit or adding the path of a compiled one on you machine.
4. Run the demo script to test the tracker:
   |>> demo_TADT

Publication

Details about the TADT tracker can be found in the CVPR 2019 paper:
Target-Aware Deep Tracking
Xin Li, Chao Ma, Baoyuan Wu, Zhenyu He, Ming-Hsuan Yang.
In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.

Please cite the above publication, if you find the code helpful in your research.

Bibtex:
@inproceedings{TADT,
author = {Li, Xin and Ma, Chao and Wu, Baoyuan and He, Zhenyu and Yang, Ming-Hsuan},
title = {Target-Aware Deep Tracking},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
year = {2019}
}

Raw results

[OTB] [VOT] [TC128]

Project webpage

https://xinli-zn.github.io/TADT-project-page/

Other implementations

[pytorch]

Contact

Email: [email protected]
Homepage: https://sites.google.com/view/xinli-homepage