交互式跟踪：一种具有记忆增强适应的人机回环范式
Interactive Tracking: A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation
提出交互式跟踪新范式，允许用户通过自然语言指令实时引导跟踪器，并引入动态记忆机制从反馈中学习；为视觉跟踪研究提供了新基准和基线，推动人机协同的跟踪系统发展。
原文依据 we introduce Interactive Tracking, a new paradigm that allows users to guide the tracker at any time using natural language commands.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的视觉跟踪器主要以非交互、发射后不管的方式运行，这使得它们不适用于需要人机回环适应的现实场景。为了克服这一局限，我们引入了交互式跟踪，这是一种允许用户随时使用自然语言命令引导跟踪器的新范式。为了支持这一方向的研究，我们做出了三项主要贡献。首先，我们提出了InteractTrack，这是首个用于交互式跟踪的大规模基准，包含150个视频，带有密集的边界框标注和带时间戳的语言指令。其次，我们提出了一个全面的评测协议，并评估了25个代表性跟踪器，表明最优方法在交互场景中失败——在传统基准上的强劲性能并不能迁移。第三，我们引入了交互式记忆增强跟踪（IMAT），这是一个新的基线，采用动态记忆机制从用户反馈中学习并相应地更新跟踪行为。我们的基准、协议和基线为开发更智能、自适应和协作的跟踪系统奠定了基础，弥合了自动感知与人类引导之间的差距。完整的基准、跟踪结果和分析可在\href https://github.com/NorahGreen/InteractTrack.git 此URL获取。
英文原文摘要 1361 字符
Existing visual trackers mainly operate in a non-interactive, fire-and-forget manner, making them impractical for real-world scenarios that require human-in-the-loop adaptation. To overcome this limitation, we introduce Interactive Tracking, a new paradigm that allows users to guide the tracker at any time using natural language commands. To support research in this direction, we make three main contributions. First, we present InteractTrack, the first large-scale benchmark for interactive tracking, containing 150 videos with dense bounding box annotations and timestamped language instructions. Second, we propose a comprehensive evaluation protocol and evaluate 25 representative trackers, showing that state-of-the-art methods fail in interactive scenarios--strong performance on conventional benchmarks does not transfer. Third, we introduce Interactive Memory-Augmented Tracking (IMAT), a new baseline that employs a dynamic memory mechanism to learn from user feedback and update tracking behavior accordingly. Our benchmark, protocol, and baseline establish a foundation for developing more intelligent, adaptive, and collaborative tracking systems, bridging the gap between automated perception and human guidance. The full benchmark, tracking results, and analysis are available at \href https://github.com/NorahGreen/InteractTrack.git this URL .