Efficient Plug-and-Play Mamba-Based Selective Target State Modeling for Lightweight Visual Tracking

View at publisher Summarise with VIRAT
Authors: Yao Chen, Guancheng Jia, Yufei Zha, Peng Zhang
Cited by: 0
References: 47

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Temporal target state modeling is essential for robust visual tracking, yet existing approaches often rely on deep or iterative architectures that incur excessive computational and parametric costs, making them unsuitable for lightweight real-time deployment. To address this challenge, we propose TSTrack, the first lightweight tracking framework that integrates a State Space Model (SSM). TSTrack consists of two innovative modules: (1) Target-Aware Mamba (TAM): It enables low-latency adaptive temporal modeling by fusing real-time search states, static templates, and compressed historical context in Mamba's hidden states through selective bidirectional interaction. As a plug-and-play module, TAM improves the performance of existing lightweight trackers with minor computational and parameter increase (approximately +6% parameters and +1% MACs); (2) Spatial-Channel Aggregation Module (SCAM): It hierarchically refines target features via dual-path attention that coordinates spatial activation enhancement and channel-wise feature recalibration, boosting localization precision in complex scenarios. Our TSTrack achieves promising tracking speed with competitive tracking performance. For instance, it suppresses previous lightweight tracking methods across six commonly used tracking benchmarks, such as LaSOT, GOT-10k, and TrackingNet. Simultaneously, it can run at 41$fps$on CPU devices. This work redefines efficiency-accuracy trade-offs in lightweight visual tracking and advances temporal modeling theory in resource-constrained computer vision tasks. The source code is available athttps://github.com/Xiaochen918/TSTrack.

Fields of Study & Subjects

Video Surveillance and Tracking Methods Advanced Neural Network Applications Visual Attention and Saliency Detection

Publication details

Journal / source
IEEE Transactions on Multimedia
Volume
28
Pages
7852–7863
Publication date
1 January 2026
Language
EN