arXiv:2512.10102cs.CV2025-12中稿 · WACV 2026

提出分层实例追踪任务,兼顾隐私保护与信息可用性。

Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information

  • 构建分层实例追踪新任务,保持物体与部件的层级关系。
  • 发布首个支持该任务的数据集,含552段视频、2765个实体。
  • 适合关注隐私保护与视觉追踪融合的研究者。

我们提出一项新任务——分层实例追踪,旨在追踪预定义类别中所有物体与部件的实例,并保持其层级关系。为此,我们构建了首个支持该任务的基准数据集,包含552段视频、2765个唯一实体,归属40个类别(涵盖物体与部件)。对四种模型的七种变体在该任务上的评估表明,该数据集具有挑战性。数据集已公开:https://vizwiz.org/tasks-and-datasets/hierarchical-instance-tracking/

原文摘要 · Abstract (English)

We propose a novel task, hierarchical instance tracking, which entails tracking all instances of predefined categories of objects and parts, while maintaining their hierarchical relationships. We introduce the first benchmark dataset supporting this task, consisting of 2,765 unique entities that are tracked in 552 videos and belong to 40 categories (across objects and parts). Evaluation of seven variants of four models tailored to our novel task reveals the new dataset is challenging. Our dataset is available at https://vizwiz.org/tasks-and-datasets/hierarchical-instance-tracking/

实例追踪隐私保护数据集

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。