The official repository for NT-VOT211, introduced in:
- ACCV 2024 (Oral, Best Application Paper Honorable Mention): NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking
- IJCV 2026 (Extended Journal Version): A Comprehensive Benchmark for Evaluating Night-time Visual Object Tracking
Yu Liu, Arif Mahmood, Muhammad Haris Khan
- 2025-12: 🎉 Our extended work, A Comprehensive Benchmark for Evaluating Night-time Visual Object Tracking, has been accepted by International Journal of Computer Vision (IJCV)! Link
- 2024-12: 🏆 NT-VOT211 won ACCV’24 Best Application Paper Honorable Mention!
- 2024-09: NT-VOT211 is accepted as ACCV 2024 Oral Presentation.
👇👇👇 extended code 👇👇👇👇
Code for newly introduced components in the extended paper
☝️☝️☝️ extended code ☝️☝️☝️☝️
🔥🔥🔥 We will regularly update the links to the top three trackers right here ⬇️
| Tracker | AUC | Tracker | Precision |
|---|---|---|---|
| ProContEXT | 40.10 | ODTrack | 55.80 |
| KeepTrack | 39.60 | KeepTrack | 55.50 |
| ODTrack | 39.60 | ProContEXT | 54.50 |
🔥🔥🔥 We will regularly update the links to the top three trackers right here ⬆️
We maintain two complete leaderboards: one is featured on Papers with Code, and the other is on EvalAI. To submit a record on EvalAI, please adhere to the following instructions.
Many current visual object tracking benchmarks such as OTB100, NfS, UAV123, LaSOT, and GOT-10K, predominantly contain day-time scenarios while the challenges posed by the night-time has been less investigated. It is primarily because of the lack of a large-scale, well-annotated night-time benchmark for rigorously evaluating tracking algorithms. To this end, this paper presents NT-VOT211, a new benchmark tailored for evaluating visual object tracking algorithms in the challenging night-time conditions. NT-VOT211 consists of 211 diverse videos, offering 211,000 well-annotated frames with 8 attributes including camera motion, deformation, fast motion, motion blur, tiny target, distractors, occlusion and out-of-view.
You can download our dataset here.
Please follow these step-by-step instructions to evaluate your algorithm.
Challenge Phases: Please note that our challenge is divided into two phases: the public phase and the private phase.
- In the private phase, you are allowed to submit a maximum of 100 submissions per day.
- In the public phase, you are limited to a maximum of 1 submission per month.
We have implemented these limits to maintain a clean and readable leaderboard. We encourage all challengers to submit only their most competitive results on the public leaderboard. To evaluate your results, please follow this tutorial.
Annotation tool and meta information can be found here.
If you find our work valuable, we kindly ask you to consider citing our paper and starring ⭐ our repository. Our implementation includes dataset and useful tools and we hope it make life easier for the VOT research community.
@inproceedings{liu2024ntvot,
title={NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking},
author={Yu Liu and Arif Mahmood and Muhammad Haris Khan},
booktitle={Proceedings of the Asian Conference on Computer Vision (ACCV)},
pages={to be announced},
year={2024},
organization={Springer}
}
@article{liu2026comprehensive,
title={A Comprehensive Benchmark for Evaluating Night-time Visual Object Tracking},
author={Liu, Yu and Mahmood, Arif and Khan, Muhammad Haris},
journal={International Journal of Computer Vision},
volume={134},
pages={21},
year={2026},
publisher={Springer},
doi={10.1007/s11263-025-02661-7},
url={https://doi.org/10.1007/s11263-025-02661-7}
}
The dataloader code borrows heavily from PyTracking.
Please open a GitHub issue for any help. If you have any questions regarding the technical details, feel free to contact us.