Salvato in:
Dettagli Bibliografici
Autori principali: Kang, Ben, Zhao, Jie, Chen, Xin, Geng, Wanting, Zhang, Bin, Zhang, Lu, Wang, Dong, Lu, Huchuan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.01412
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911481009799168
author Kang, Ben
Zhao, Jie
Chen, Xin
Geng, Wanting
Zhang, Bin
Zhang, Lu
Wang, Dong
Lu, Huchuan
author_facet Kang, Ben
Zhao, Jie
Chen, Xin
Geng, Wanting
Zhang, Bin
Zhang, Lu
Wang, Dong
Lu, Huchuan
contents With growing real-world demands, efficient tracking has received increasing attention. However, most existing methods are limited to RGB inputs and struggle in multi-modal scenarios. Moreover, current multi-modal tracking approaches typically use complex designs, making them too heavy and slow for resource-constrained deployment. To tackle these limitations, we propose UETrack, an efficient framework for single object tracking. UETrack demonstrates high practicality and versatility, efficiently handling multiple modalities including RGB, Depth, Thermal, Event, and Language, and addresses the gap in efficient multi-modal tracking. It introduces two key components: a Token-Pooling-based Mixture-of-Experts mechanism that enhances modeling capacity through feature aggregation and expert specialization, and a Target-aware Adaptive Distillation strategy that selectively performs distillation based on sample characteristics, reducing redundant supervision and improving performance. Extensive experiments on 12 benchmarks across 3 hardware platforms show that UETrack achieves a superior speed-accuracy trade-off compared to previous methods. For instance, UETrack-B achieves 69.2% AUC on LaSOT and runs at 163/56/60 FPS on GPU/CPU/AGX, demonstrating strong practicality and versatility. Code is available at https://github.com/kangben258/UETrack.
format Preprint
id arxiv_https___arxiv_org_abs_2603_01412
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UETrack: A Unified and Efficient Framework for Single Object Tracking
Kang, Ben
Zhao, Jie
Chen, Xin
Geng, Wanting
Zhang, Bin
Zhang, Lu
Wang, Dong
Lu, Huchuan
Computer Vision and Pattern Recognition
With growing real-world demands, efficient tracking has received increasing attention. However, most existing methods are limited to RGB inputs and struggle in multi-modal scenarios. Moreover, current multi-modal tracking approaches typically use complex designs, making them too heavy and slow for resource-constrained deployment. To tackle these limitations, we propose UETrack, an efficient framework for single object tracking. UETrack demonstrates high practicality and versatility, efficiently handling multiple modalities including RGB, Depth, Thermal, Event, and Language, and addresses the gap in efficient multi-modal tracking. It introduces two key components: a Token-Pooling-based Mixture-of-Experts mechanism that enhances modeling capacity through feature aggregation and expert specialization, and a Target-aware Adaptive Distillation strategy that selectively performs distillation based on sample characteristics, reducing redundant supervision and improving performance. Extensive experiments on 12 benchmarks across 3 hardware platforms show that UETrack achieves a superior speed-accuracy trade-off compared to previous methods. For instance, UETrack-B achieves 69.2% AUC on LaSOT and runs at 163/56/60 FPS on GPU/CPU/AGX, demonstrating strong practicality and versatility. Code is available at https://github.com/kangben258/UETrack.
title UETrack: A Unified and Efficient Framework for Single Object Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.01412