MVLM：基于视觉-语言边界置信度与记忆门控跟踪的无模板跟踪
MVLM: Template-Free Tracking via Vision-Language Margin Confidence and Memory-Gated Tracking
用视觉-语言相关性与时序记忆构造 margin 置信度，并据此在紧凑 ROI 搜索与全局重定位之间动态切换，为无模板、纯语言指定的跟踪提供了一种可复用的置信度门控搜索策略。
原文依据 MVLM dynamically gates the search region--switching between compact ROI (Region of Interest) search and global re-localization
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出一种仅基于自然语言的全新无模板跟踪范式，能够跟踪任意物体，并在无需框初始化的情况下无缝切换到新目标。我们的核心思想是通过视觉-语言（VL）相关性来定位物体。然而，由于空间不确定性以及视觉-语言显著性的模糊性，仅使用相关性在大搜索区域下是脆弱的。为解决这些问题，我们提出 MVLM，一种基于记忆的视觉-语言边界置信度，它融合了视觉-语言相关性、编码器预测与时序记忆。MVLM 动态地对搜索区域进行门控——在紧凑的 ROI（感兴趣区域）搜索与全局重定位之间切换——以降低空间不确定性。在理论上，我们推导了将 MVLM 分数与跟踪概率相联系的界，刻画了 ROI 内的误定位概率与 ROI 排除概率。通过大量评估，我们验证了定理，并仅使用语言引导在多个基准（TNL2K、LaSOT、OTB99 与 MGIT）上取得了最优性能。
英文原文摘要 1063 字符
We introduce a new template-free tracking paradigm based solely on natural language, capable of tracking an arbitrary object and seamlessly switching to a new target without box initialization.Our key idea is to localize an object via vision-language (VL) correlation.However, using the correlation alone is brittle under large search regions due to spatial uncertainty and ambiguous VL saliency. To resolve these, we propose MVLM, a memory-based vision-language margin confidence that integrates vision-language correlation, encoder prediction, and temporal memory.MVLM dynamically gates the search region--switching between compact ROI (Region of Interest) search and global re-localization--to reduce spatial uncertainty. Theoretically, we derive bounds that connect the MVLM score to tracking probability, characterizing mis-localization within ROI and ROI-exclusion probabilities.Through extensive evaluation, we validate our theorems and achieve state-of-the-art performance on several benchmarks (TNL2K, LaSOT, OTB99 and MGIT) using only language guidance.