This is the official PyTorch implementation of our paper:
Multiple Object Tracking as ID Prediction
🎓 Ruopeng Gao, Ji Qi, Limin Wang
📧 Primary contact: ruopenggao@gmail.com
TL; DR. We propose a novel perspective to regard the multiple object tracking task as an in-context ID prediction problem. Given a set of trajectories carried with ID information, MOTIP directly decodes the ID labels for current detections, which is straightforward and effective.
- 2025.03.25: Our revised paper is released at arXiv:2403.16848. The latest codebase is being organized 🚧.
- 2025.02.27: Our paper is accepted by CVPR 2025 🎉 🎉. The revised paper and a more efficient codebase will be released in March. Almost there 🤓 ~
- 2024.03.26: The first version of our paper is released at arXiv:2403.16848v1 📌. The corresponding codebase is stored in the prev-engine branch (No longer maintained starting April 2025 ⛔).
This project is built upon Deformable DETR, MOTR, TrackEval. Thanks to the contributors of these great codebases.
If you think this project is helpful, please feel free to leave a ⭐ and cite our paper:
@article{MOTIP,
title={Multiple Object Tracking as ID Prediction},
author={Gao, Ruopeng and Qi, Ji and Wang, Limin},
journal={arXiv preprint arXiv:2403.16848},
year={2024}
}