@inproceedings{d1c4d3238a234f58b533d35b25828252,
title = "MSTracker: A Multi-scale Spatio-temporal Framework for UAV Multi-Object Tracking",
abstract = "Aiming at the challenges of trajectory fragmentation and identity switches caused by similar appearances and frequent occlusions in Unmanned Aerial Vehicle (UAV) aerial videos, this paper proposes a novel Multi-scale Spatio-temporal tracking framework, termed MSTracker. The core of MSTracker consists of three key components: 1) A Multi-Scale Feature Extraction model with a Feature Map Quality Weighting Scheme to enhance target representation; 2) A Spatio-Temporally Guided Trajectory Update Model that leverages long-term context and dynamic trajectory management to reduce identity switches; 3) A Dynamically Weighted Fusion Loss for improved training. On the VisDrone-MOT dataset, MSTracker achieves state-of-the-art performance with 58.2\% IDF1 and 41.0\% MOTA, demonstrating significant effectiveness in challenging UAV scenarios.",
keywords = "Multi-scale Feature Encoding, Spatio-temporal Information Fusion, Trajectory Management, UAV multi-object tracking",
author = "Yan Ding and Minjin Zhao and Yuchen Ling and Shupeng Guo and Yixiao Fan and Luheng Cui",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 4th International Conference on Intelligent Computing and Next Generation Networks, ICNGN 2025 ; Conference date: 12-12-2025 Through 14-12-2025",
year = "2025",
doi = "10.1109/ICNGN67480.2025.11413772",
language = "English",
series = "Proceedings of the 4th International Conference on Intelligent Computing and Next Generation Networks, ICNGN 2025",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
editor = "Lee, \{Gyu Myoung\} and Pavel Loskot and Qinmin Yang and Ruidan Su",
booktitle = "Proceedings of the 4th International Conference on Intelligent Computing and Next Generation Networks, ICNGN 2025",
address = "United States",
}