Dual-Modaltiy Single Object Tracking using Python3

This gigthub provides part of PyTorch implementation of baseline trackers used in VisEvent single object tracking benchmark [VisEvent-SOT-Benchmark]

VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows, Xiao Wang, Jianing Li, Lin Zhu, Zhipeng Zhang, Zhe Chen, Xin Li, Yaowei Wang, Yonghong Tian, Feng Wu [Paper] [Project] [DemoVideo] [VideoTutorial]

1. Real-Time MDNet: Single Modality Version:

Download the file: realtimeMDNet-python3.tar.gz

2. Real-Time MDNet: Dual-Modality Version:

Download the file: realtimeMDNet-visEvent-python3.x.tar.gz (based on Visible and Event images)

3. Real-Time MDNet: Cross-Modality Transformer based Dual-Modality Fusion Version:

Download the file: [[realtimeMDNet-visEvent-CMT(ALL)-python3.tar.gz](https://github.com/wangxiao5791509/RGB-DVS-SOT-Baselines/blob/main/realtimeMDNet-visEvent-CMT(ALL)-python3.tar.gz)] (based on Visible and Event images)

4. pyMDNet:VisEvent Tracking:

Download the file: [pyMDNet-VisEvent-master.tar.gz]

5. VisEvent Tracking (Meta-Tracker):

Download the file from: [Meta-Tracker]

6. SiamFC based VisEvent Tracking:

Download the file from: [visEvent_siamfc_pytorch.tar.gz]

7. MANet based VisEvent Tracking:

Download the file from: [MANet_VisEvent_master.tar.gz]

8. pyVITAL based VisEvent tracking:

Download the file from: [pyVITAL-VisEvent-master]

9. Correlation Filter based VisEvent Tracking:

(10 trackers are supported: 1. KCF_HOG 2. STRCF 3. MOSSE 4. CSK 5. CN 6. DAT 7. ECO-HC 8. BACF 9. CSRDCF 10. LDES) Download the file from: [pyCFTrackers_visEvent_master.tar.gz]

📃 BibTex:

If you find this work useful for your research, please cite the following papers:

@article{wang2021viseventbenchmark,
  title={VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows},
  author={Xiao Wang, Jianing Li, Lin Zhu, Zhipeng Zhang, Zhe Chen, Xin Li, Yaowei Wang, Yonghong Tian, Feng Wu},
  journal={arXiv:2108.05015},
  year={2021}
}

If you have any questions about this work, please submit an issue or contact me via Email: wangxiaocvpr@foxmail.com. Thanks for your attention!