真实场景下穿越容器与遮挡物的目标跟踪
Tracking through Containers and Occluders in the Wild
AI总结：
针对杂乱动态环境下目标跟踪难题，本文提出TCOW基准与模型，构建合成加真实标注的混合数据集，评估发现现有Transformer视频模型距真正具备物体恒存性仍有较大性能差距。
摘要：
在杂乱动态环境中实现具备持久性的目标跟踪，仍是计算机视觉系统面临的一大难题。本文提出了TCOW（穿越遮挡与容器跟踪），这是一个用于重度遮挡与容纳场景下视觉跟踪的全新基准与模型。我们设定了一项任务：给定一段视频序列，需分割出目标物体的投影范围，同时在存在容器或遮挡物时，分割出其周围的容器或遮挡物。为研究该任务，我们构建了合成数据集与标注真实数据集的混合数据集，既支持监督学习，也支持在多种任务变化形式（如移动容纳或嵌套容纳）下对模型性能进行结构化评估。我们评估了两种最新的基于transformer的视频模型，结果发现，尽管它们在特定任务变化设置下跟踪目标的能力出人意料地强，但要宣称跟踪模型已真正具备物体恒存性概念，仍存在相当大的性能差距。
英文摘要：
Tracking objects with persistence in cluttered and dynamic environments remains a difficult challenge for computer vision systems. In this paper, we introduce $\textbf{TCOW}$, a new benchmark and model for visual tracking through heavy occlusion and containment. We set up a task where the goal is to, given a video sequence, segment both the projected extent of the target object, as well as the surrounding container or occluder whenever one exists. To study this task, we create a mixture of synthetic and annotated real datasets to support both supervised learning and structured evaluation of model performance under various forms of task variation, such as moving or nested containment. We evaluate two recent transformer-based video models and find that while they can be surprisingly capable of tracking targets under certain settings of task variation, there remains a considerable performance gap before we can claim a tracking model to have acquired a true notion of object permanence.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
