用点击操作实现实时交互式单目标跟踪，提升初始化精度。
ClickTrack: Towards Real-time Interactive Single Object Tracking
- 通过点击输入结合文本提示，生成精准目标框用于跟踪。
- 在LaSOT和GOT-10k上表现稳定，支持实时交互场景。
- 可集成至SAM模型，缓解点输入带来的歧义问题。
单目标跟踪依赖精确的目标边界框初始化。本文重新审视现有初始化方法的不足，提出一种新范式ClickTrack，利用点击交互实现实时场景下的单目标跟踪。由于点击本身缺乏层次信息，针对特殊场景中的模糊性，设计了引导式点击修正器（GCR），接受点及可选文本信息输入，将点转换为操作者期望的边界框，作为跟踪器输入。在LaSOT和GOT-10k基准上的实验表明，结合GCR的跟踪器在实时交互场景中表现稳定。此外，将GCR融入分割任意模型（SAM）中，显著降低了SAM接收点输入时的歧义问题。
原文摘要 · Abstract (English)
Single object tracking(SOT) relies on precise object bounding box initialization. In this paper, we reconsidered the deficiencies in the current approaches to initializing single object trackers and propose a new paradigm for single object tracking algorithms, ClickTrack, a new paradigm using clicking interaction for real-time scenarios. Moreover, click as an input type inherently lack hierarchical information. To address ambiguity in certain special scenarios, we designed the Guided Click Refiner(GCR), which accepts point and optional textual information as inputs, transforming the point into the bounding box expected by the operator. The bounding box will be used as input of single object trackers. Experiments on LaSOT and GOT-10k benchmarks show that tracker combined with GCR achieves stable performance in real-time interactive scenarios. Furthermore, we explored the integration of GCR into the Segment Anything model(SAM), significantly reducing ambiguity issues when SAM receives point inputs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。