发表机构
Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Nanyang Technological University; University of Science and Technology Beijing; Tsinghua University（中国科学院计算技术研究所; 中国科学院大学; 南洋理工大学; 北京科技大学; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对低资源IMU人体活动识别，提出覆盖感知的虚拟IMU增强框架，通过选择锚点、生成候选并按可靠性加权，提升识别性能。
AI 中文摘要
基于IMU的人体活动识别（HAR）利用可穿戴传感器实现对日常活动的连续、隐私友好的监测。然而，构建能够跨不同用户和现实条件泛化的可靠HAR模型需要大量标记的IMU数据，而这些数据的采集成本高昂且困难。现有方法主要依赖增强或合成来扩充可用数据，但不加区分地添加虚拟样本可能提供很少的新覆盖范围，并引入不可靠的监督。为克服这些挑战，我们提出了一种新颖的覆盖感知的虚拟IMU增强框架，该框架决定在何处补充真实数据、如何生成和选择虚拟候选样本，以及在训练期间如何对其加权。具体而言，我们在学习的传感器嵌入空间中选择多样性和稀缺性锚点，将锚点动态转换为提示，并为每个锚点生成虚拟IMU候选样本。然后，我们通过结合锚点接近度和标签一致性的选择成本对候选样本进行排序，并将选中的候选样本以基于可靠性的权重纳入HAR训练。在公开HAR基准上的实验表明，我们的方法在识别性能上持续优于竞争基线，消融研究证实了所提出框架设计的有效性。
英文摘要
IMU-based human activity recognition (HAR) enables continuous, privacy-friendly monitoring of daily activities using wearable sensors. However, building reliable HAR models that generalize across diverse users and real-world conditions requires large amounts of labeled IMU data, which are expensive and difficult to collect. Existing approaches mainly rely on augmentation or synthesis to expand available data, but indiscriminately adding virtual samples may provide little new coverage and introduce unreliable supervision. To overcome these challenges, we propose a novel coverage-aware virtual IMU augmentation framework that decides where to supplement real data, how to generate and select virtual candidates, and how strongly to weight them during training. Specifically, we select diversity and scarcity anchors in a learned sensor embedding space, convert anchor dynamics into prompts, and generate virtual IMU candidates for each anchor. We then rank candidates by a selection cost combining anchor proximity and label consistency, and incorporate the selected candidates into HAR training with reliability-based weights. Experiments on public HAR benchmarks show that our method consistently improves recognition performance over competitive baselines, and ablation studies confirm the effectiveness of the proposed framework design.
