连续令牌级时空上下文建模用于视觉目标跟踪
Continuous Token-Level Spatio-Temporal Context Modeling for Visual Object Tracking
浏览论文内容
中文总结 AI 辅助
针对现有跟踪方法离散采样偏离时空连续性导致性能下降的问题，提出TLCTrack框架，通过MUA、SSTC和TSTB模块实现连续令牌级时空上下文建模，在五个基准上超越现有最先进跟踪器。
中文摘要 AI 辅助
时空上下文对于视觉跟踪变得越来越关键。然而，大多数现有方法通过离散采样策略提取时空线索，这本质上偏离了时空上下文的连续性，从而降低了跟踪性能。为了解决这一挑战，我们提出了TLCTrack，一种新颖的跟踪框架，通过持续更新的显著令牌来建模令牌级时空上下文，从而实现更准确的目标表示。具体来说，TLCTrack包含三个组件：掩码单向注意力（MUA）、空间显著令牌收集（SSTC）和时间显著令牌库（TSTB）模块。通过显式整合时空上下文，MUA在搜索区域中提取具有判别性的目标感知空间特征。为了避免背景对特征学习的负面影响，SSTC逐步抑制背景干扰，从而增强目标的空间表示。最后，TSTB通过连续的显著令牌更新捕获高质量的时空信息。在五个基准上的大量实验表明，我们的方法在性能上优于最先进的跟踪器。代码和模型可在该https URL获取。
英文摘要
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.
发表机构
- Xi’an Jiaotong University（西安交通大学）
- College of Electrical Engineering, Zhejiang University（浙江大学电气工程学院）
机构由 AI 辅助整理，请以论文原文为准。
