UncTrack: Reliable Visual Object Tracking With Uncertainty-Aware Prototype Memory Network

doi:10.1109/TIP.2025.3559796

	UncTrack: Reliable Visual Object Tracking With Uncertainty-Aware Prototype Memory Network
	Yao, Siyuan 1; Guo, Yang 1; Yan, Yanyang 2; Ren, Wenqi 3; Cao, Xiaochun 3
	2025
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	34 页码:3533-3546
摘要	Transformer-based trackers have achieved promising success and become the dominant tracking paradigm because of their accuracy and efficiency. Despite the substantial progress, most of the existing approaches handle object tracking as a deterministic coordinate regression problem, while the target localization uncertainty has been largely overlooked, which hampers trackers' ability to maintain reliable target state prediction in challenging scenarios. To address this issue, we propose UncTrack, a novel uncertainty-aware transformer-based tracker that predicts the target localization uncertainty and incorporates this uncertainty information for accurate target state inference. Specifically, UncTrack uses a transformer encoder to perform feature interactions between the template and search images. The output features are passed into an uncertainty-aware localization decoder (ULD) to coarsely predict the corner-based localization and the corresponding localization uncertainty. Then, the localization uncertainty is sent into a prototype memory network (PMN) to excavate valuable historical information to identify whether the target state prediction is reliable. To enhance the template representation, the samples with high confidence are fed back into the prototype memory bank for memory updating, which makes the tracker more robust to challenging appearance variations. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods. Our code is available at https://github.com/ManOfStory/UncTrack
关键词	Uncertainty Location awareness Target tracking Transformers Reliability Prototypes Object tracking Visualization Accuracy Training Reliable object tracking uncertainty estimation prototype memory network memory updating
DOI	10.1109/TIP.2025.3559796
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62402055] ; National Natural Science Foundation of China[62302480] ; Shenzhen Science and Technology Program[KQTD20221101093559018]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001506596200013
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42342
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Cao, Xiaochun
作者单位	1.Beijing Univ Posts & Telecommun, Sch Comp Sci, Natl Pilot Software Engn Sch, Beijing 100876, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100190, Peoples R China 3.Sun Yat Sen Univ, Sch Cyber Sci & Technol, Shenzhen Campus, Shenzhen 518107, Peoples R China
推荐引用方式 GB/T 7714	Yao, Siyuan,Guo, Yang,Yan, Yanyang,et al. UncTrack: Reliable Visual Object Tracking With Uncertainty-Aware Prototype Memory Network[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2025,34:3533-3546.
APA	Yao, Siyuan,Guo, Yang,Yan, Yanyang,Ren, Wenqi,&Cao, Xiaochun.(2025).UncTrack: Reliable Visual Object Tracking With Uncertainty-Aware Prototype Memory Network.IEEE TRANSACTIONS ON IMAGE PROCESSING,34,3533-3546.
MLA	Yao, Siyuan,et al."UncTrack: Reliable Visual Object Tracking With Uncertainty-Aware Prototype Memory Network".IEEE TRANSACTIONS ON IMAGE PROCESSING 34(2025):3533-3546.