构建真实警察执法视频基准数据集，助力高风险行为识别研究
EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage
- 聚焦真实执法场景，标注秒级关键动作
- 模型对
- 武器出
我们提出EgoPolice，一个精心筛选的真实第一人称警察-市民互动数据集，源自公开的执法记录仪视频。选取对警务行为研究至关重要的动作标签，并以秒级粒度进行标注。视频包含快速不规则镜头运动、密集人际交互及罕见高危事件，构成对运动鲁棒性与情境感知能力的严峻挑战。提供分类与多选问答两类任务，对开源与闭源模型进行基准测试。结果显示，即使顶尖视频模型Gemini 2.5 Pro在预测“武器出”等高风险行为时仍表现不佳。除作为基准外，EgoPolice为大规模执法视频库中兴趣事件的自动识别提供基础，可提升后续人工审核效率。
原文摘要 · Abstract (English)
We introduce EgoPolice, a carefully curated dataset of real, egocentric police-civilian interactions, sourced from publicly available body-worn camera videos. We select police-civilian action labels that are critical for police behavioral research and annotate them at a second-by-second granularity. The videos feature rapid and irregular camera motion, dense human interactions, and rare high-stakes events, making the dataset a challenging benchmark for motion-robust and context-aware egocentric perception. We provide two different tasks, classification and multiple-choice question-answering, and benchmark both open-source and closed-source models. We find that even the best video models like Gemini 2.5 Pro still struggle to accurately predict high-risk actions such as "Weapon Out". Beyond serving as a benchmark, EgoPolice provides a foundation for developing models capable of identifying events of interest in large-scale body-worn camera video repositories, enabling more efficient downstream human review.
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。