Mamba based visual object tracking

💥 News

• [2025.07.01] Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Tracking, Shiao Wang, Ju Huang, Qingchuan Ma, Jinfeng Gao, Chunyi Xu, Xiao Wang*, Lan Chen*, Bo Jiang, arXiv:2506.23783 is released on [arXiv]
• [2024.06.25] This work is accepted by PRCV-2024 [第七届中国模式识别与计算机视觉大会 (The 7th Chinese Conference on Pattern Recognition and Computer Vision PRCV 2024)].
• [2024.05.15] Source code and weights are all released.
• [2024.04.28] The arXiv paper is released [arXiv]

🔨 Environment Settings

• Install environment using conda

conda create -n mamba_fetrack python=3.10.13
conda activate mamba_fetrack

• Install the package for Vim

conda install cudatoolkit==11.8 -c nvidia
pip install torch==2.1.1 torchvision==0.16.1 torchaudio==2.1.1 --index-url https://download.pytorch.org/whl/cu118
conda install -c "nvidia/label/cuda-11.8.0" cuda-nvcc
conda install packaging
pip install -r vim_requirements.txt

• Install the mamba-1.1.1 and casual-conv1d-1.1.3 for mamba

Download the mamba-1.1.1 and source code and place it in the project path. Go to source code and install the corresponding environment.

cd mamba-1.1.1
pip install .

Download the casual-conv1d-1.1.3 and source code and place it in the project path. Go to source code and install the corresponding environment.

cd ..
cd causal-conv1d-1.1.3
pip install .

• Install the package for tracking

bash install.sh

• Run the following command to set paths for this project

python tracking/create_default_local_file.py --workspace_dir . --data_dir ./data --save_dir ./output

• After running this command, you can also modify paths by editing these two files

lib/train/admin/local.py  # paths about training
lib/test/evaluation/local.py  # paths about testing

💘 Acknowledgment

[OSTrack] [Mamba] [FELT] [CEUTrack] [FE108]

📰 Citation

If you think this paper is helpful, please feel free to leave a star ⭐️ and cite our paper:

@inproceedings{huang2024mamba,
  title={Mamba-fetrack: Frame-event tracking via state space model},
  author={Huang, Ju and Wang, Shiao and Wang, Shuai and Wu, Zhe and Wang, Xiao and Jiang, Bo},
  booktitle={Chinese Conference on Pattern Recognition and Computer Vision (PRCV)},
  pages={3--18},
  year={2024},
  organization={Springer}
}

@misc{wang2025mambafetrackv2revisitingstate,
      title={Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Tracking}, 
      author={Shiao Wang and Ju Huang and Qingchuan Ma and Jinfeng Gao and Chunyi Xu and Xiao Wang and Lan Chen and Bo Jiang},
      year={2025},
      eprint={2506.23783},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}