RBO

The official implementation of the CVPR 2022 paper Ranking-Based Siamese Visual Tracking

Introduction

this paper proposes a ranking-based optimization algorithm to explore the relationship among different proposals for Siamese trackers.

Environment

Tracking Results

The raw results of SiamRPN++-RBO can be found here.

Clone the GIT repository.

git clone https://github.com/sansanfree/RBO.git

Evaluation on the SiamRPN++-RBO

Please refer to the README

Evaluation on the SiamPW-RBO

coming soon

Evaluation on the SiamBAN-RBO

coming soon

Citation

If you find this work useful for your research, please consider citing our work:

@inproceedings{Tang_2022_Ranking,
    title={Ranking-Based Siamese Visual Tracking},
    author={Feng, Tang and Qiang Ling},
    booktitle={The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2022}
}

Contact

If you have any questions, please feel free to contact tang0420@mail.ustc.edu.cn

Acknowledgments

Thanks for the SiamRPN++(https://github.com/STVIR/pysot) and SiamBAN(https://github.com/hqucv/siamban) Libraries, which helps us to quickly implement our ideas.