Continuous Token-Level Spatio-Temporal Context Modeling for Visual Object Tracking

2026-09-07

AI Summary

为解决视觉跟踪中时空上下文连续性问题，提出TLCTrack框架，通过持续更新显著令牌来建模时空上下文，提高跟踪准确性。

Abstract

Spatio-temporal context has become increasingly crucial for visual tracking. However, most existing approaches extract spatio-temporal cues via discrete sampling strategies, which inherently deviate from the continuity of spatio-temporal context, thereby deteriorating tracking performance. To address this challenge, we propose TLCTrack, a novel tracking framework that models token-level spatio-temporal context through continuously updated salient tokens, enabling more accurate target representation. Specifically, TLCTrack incorporates three components: Masked Unidirectional Attention (MUA), Spatial Salient Token Collection (SSTC), and Temporal Salient Token Bank (TSTB) modules. By explicitly integrating spatio-temporal context, MUA extracts discriminative targetaware spatial features in the search region. To avoid the negative impact of background on feature learning, SSTC progressively suppresses background interference, thereby enhancing target spatial representation. Finally, TSTB captures high-quality spatio-temporal information through continuous salient token updates. Extensive experiments on five benchmarks demonstrate that our method achieves superior performance over state-of-the-art trackers. Code and models are available at https://github.com/xiading123/TLCTrack.

Problem

• Spatio-temporal context
• Visual tracking
• Discrete sampling

Innovation

• Continuous Spatio-Temporal Context
• Token-Level Representation
• Masked Unidirectional Attention
• Salient Token Updates