Enhancing Visual Tracking by Leveraging High-frequency Information within Event Signals


Yuheng Jiang (University of Science and Technology of China), Hebei Li (University of Science and Technology of China), Dachun Kai (University of Science and Technology of China), Yansong Peng (University of Science and Technology of China), Jiahui Yuan (University of Science and Technology of China), Peilin Xiao (University of Science and Technology of China), Yueyi Zhang (MiroMind), Xiaoyan Sun (University of Science and Technology of China)
The 35th British Machine Vision Conference
PDFPosterVideo (Right click to download)Supplementary

Abstract

Traditional object trackers struggle in degraded scenarios, lacking sufficient appearance details of moving targets for precise tracking. Recent trackers have integrated high-frequency event signals to assist tracking. However, they neglect the high-temporal-resolution motion information inherent in events, limiting their performance especially in occlusion and background clutter. To address these challenges, we propose HFTrack, a novel tracker designed to fully leverage the spatio-temporal high-frequency information within event signals, thereby enhancing the tracking performance. Specifically, we introduce a frequency-based feature enhancement module, which enriches the frame feature with high-frequency components from events in frequency space, capturing detailed appearance information of moving targets. Additionally, we propose a spatio-temporal information decoder with an auto-regressive temporal query, integrating both historical motion cues from events and enhanced spatial features for robust target localization. Experimental results demonstrate that our HFTrack significantly outperforms existing trackers, showcasing its strong ability to track the target under challenging conditions.

Citation

@inproceedings{Jiang_2025_BMVC,
author    = {Yuheng Jiang and Hebei Li and Dachun Kai and Yansong Peng and Jiahui Yuan and Peilin Xiao and Yueyi Zhang and Xiaoyan Sun},
title     = {Enhancing Visual Tracking by Leveraging High-frequency Information within Event Signals},
booktitle = {36th British Machine Vision Conference 2025, {BMVC} 2025, Sheffield, UK, November 24-27, 2025},
publisher = {BMVA},
year      = {2025},
url       = {https://bmva-archive.org.uk/bmvc/2025/assets/papers/Paper_265/paper.pdf}
}


Copyright © 2025 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection