SUTrack: Towards Simple and Unified Single Object Tracking
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (2) · 2239-2247
DOI: 10.1609/aaai.v39i2.32223 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Xin Chen und 6 weiteren Autor:innen. Die Arbeit wurde bisher 71-mal zitiert (Crossref).
Abstract (Originalsprache)
In this paper, we propose a simple yet unified single object tracking (SOT) framework, dubbed SUTrack. It consolidates five SOT tasks (RGB-based, RGB-Depth, RGB-Thermal, RGB-Event, RGB-Language Tracking) into a unified model trained in a single session. Due to the distinct nature of the data, current methods typically design individual architectures and train separate models for each task. This fragmentation results in redundant training processes, repetitive technological innovations, and limited cross-modal knowledge sharing. In contrast, SUTrack demonstrates that a single model with a unified input representation can effectively handle various SOT tasks, eliminating the need for task-specific designs and separate training sessions. Additionally, we introduce a task-recognition training strategy and a soft token type embedding to further enhance SUTrack's performance with minimal overhead. Experiments show that SUTrack outperforms previous task-specific counterparts across 11 datasets spanning five SOT tasks. Moreover, we provide a range of models catering edge devices as well as high-performance GPUs, striking a good trade-off between speed and accuracy. We hope SUTrack could serve as a strong foundation for further compelling research into unified tracking models.
Zitieren
APA
Chen, X., Kang, B., Geng, W., Zhu, J., Liu, Y., Wang, D., & Lu, H. (2025). SUTrack: Towards Simple and Unified Single Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 39(2), 2239-2247. https://doi.org/10.1609/aaai.v39i2.32223
Vancouver
Chen X, Kang B, Geng W, Zhu J, Liu Y, Wang D, et al. SUTrack: Towards Simple and Unified Single Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(2):2239-2247. doi:10.1609/aaai.v39i2.32223
BibTeX
@article{Chen2025,
author = {Chen, Xin and Kang, Ben and Geng, Wanting and Zhu, Jiawen and Liu, Yi and Wang, Dong and Lu, Huchuan},
title = {SUTrack: Towards Simple and Unified Single Object Tracking},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {2},
pages = {2239--2247},
doi = {10.1609/aaai.v39i2.32223}
}
EUVIMED