The XFMP dataset for Explainable Fine-Grained Abnormal Behavior Recognition on Medical Personal Protective Equipment

The XFMP dataset is designed for abnormal behavior recognition on medical personal protective equipment, which features fine-grained and explainable annotations. The proper use of medical personal protective equipment (MPPE) is critical for frontline healthcare workers (HCWs) to handle highly contagious diseases. Due to the complexity of PPE donning and doffing protocols, public health organizations typically recommend having trained observers monitor the entire PPE donning and doffing process, preventing self-contamination and transmission. However, the high costs of manual monitoring impede the implementation of this practice, which makes AI-assisted PPE monitoring highly valuable. To address this, we propose an explainable and fine-grained dataset for MPPE doffing monitoring called the XFMP dataset. The dataset contains 3596 expert-annotated samples over three sub-tasks: doffing stage classification (DSC), abnormal action recognition (AAR), and critical region localization (CRL).XFMP数据集（XFMP Dataset）专为医疗个人防护装备（medical personal protective equipment，MPPE）异常行为识别任务设计，其具备细粒度且可解释的标注特性。正确穿戴与脱卸医疗个人防护装备（MPPE），是一线医护人员（healthcare workers，HCWs）应对高传染性疾病的关键保障。鉴于PPE穿戴及脱卸流程的复杂性，公共卫生机构通常会要求经培训的观察员全程监控PPE的穿戴与脱卸全流程，以防范自我污染与病毒传播。然而人工监控的高额成本极大阻碍了该实践的落地推广，因此AI辅助的PPE监控方案具有极高的应用价值。为解决这一痛点，我们构建了一款面向MPPE脱卸监控任务的可解释细粒度数据集——XFMP数据集。该数据集共包含3596份经专家标注的样本，覆盖三个子任务：脱卸阶段分类（Doffing Stage Classification，DSC）、异常动作识别（Abnormal Action Recognition，AAR）以及关键区域定位（Critical Region Localization，CRL）。

搜集汇总

背景与挑战

背景概述

XFMP数据集专为医疗个人防护装备（MPPE）的异常行为识别设计，具有细粒度和可解释的注释特点，旨在通过AI辅助监测降低医护人员在脱卸过程中的感染风险。该数据集包含3596个专家标注样本，支持脱卸阶段分类、异常动作识别和关键区域定位三个子任务，以促进可解释人工智能在公共卫生领域的应用。