HGTMT

PyTorch implementation of "Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos", IEEE Transactions on MultiMedia，paper. Feel free to contact me (xuqingyu@nudt.edu.cn) if any questions. Please cite our paper and star the repository.

VT-Tiny-MOT Dataset:

Download the VT-Tiny-MOT dataset at BaiduYun[3crl] or Google Drive.

Code:

• Create the working environment through environment.yml
• Download the transformer pvtv2 backbone from PVTv2.
• Run training/main_RGBT-Tiny_graph_gnnloss.py for training.
• Run tracking/RGBT-Tiny_private_graph_Track2_crossmodal.py for tracking.

Acknowledgement:

• This repository benefits a lot from TransCenter and GSDT.

Bibtex:

If you find this code useful, please star the project and consider citing:

@article{xu2024heterogeneous,
  title={Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos},
  author={Xu, Qingyu and Wang, Longguang and Sheng, Weidong and Wang, Yingqian and Xiao, Chao and Ma, Chao and An, Wei},
  journal={IEEE Transactions on Multimedia},
  year={2024},
  publisher={IEEE}
}