English(EN) HARMES: A Multi-Modal Dataset for Wearable Human Activity Recognition with Motion, Environmental Sensing and Sound

新的HARMES数据集结合了运动、环境和音频数据用于活动识别

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-04 13:47

研究人员推出HARMES，一个用于可穿戴人体活动识别的新多模态数据集。该数据集结合了来自腕戴设备的运动传感、环境数据和音频，总计包含20名参与者进行家务活动超过80小时的数据。HARMES旨在提高对日常生活活动的识别能力，因为单一模态的识别可能存在歧义，并且该数据集比以往同类数据集规模更大。 AI

影响提供了一个大型多模态数据集，以推进可穿戴人体活动识别领域的研究。

排序理由在arXiv上发布了一个新数据集。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.LG TIER_1 English(EN) · Robin Burchard, Pascal-Andr\'e Br\"uckner, Marius Bock, Juergen Gall, Kristof Van Laerhoven · 2026-05-05 04:00

HARMES: A Multi-Modal Dataset for Wearable Human Activity Recognition with Motion, Environmental Sensing and Sound

arXiv:2605.02596v1 Announce Type: new Abstract: With each sensing modality exhibiting inherent strengths and limitations, multi-modal approaches for wearable Human Activity Recognition (HAR) are becoming increasingly relevant -- particularly for recognizing Activities of Daily Li…
arXiv cs.LG TIER_1 English(EN) · Kristof Van Laerhoven · 2026-05-04 13:47

HARMES: A Multi-Modal Dataset for Wearable Human Activity Recognition with Motion, Environmental Sensing and Sound

With each sensing modality exhibiting inherent strengths and limitations, multi-modal approaches for wearable Human Activity Recognition (HAR) are becoming increasingly relevant -- particularly for recognizing Activities of Daily Living (ADLs), where individual modalities often p…