Several techniques have been proposed to address the problem of recognizing activities of daily living from signals. Deep learning techniques applied to inertial signals have proven to be effective, achieving significant classification accuracy. Recently, research in human activity recognition (HAR) models has been almost totally model-centric. It has been proven that the number of training samples and their quality are critical for obtaining deep learning models that both perform well independently of their architecture, and that are more robust to intraclass variability and interclass similarity. Unfortunately, publicly available datasets do not always contain hight quality data and a sufficiently large and diverse number of samples (e.g., number of subjects, type of activity performed, and duration of trials). Furthermore, datasets are heterogeneous among them and therefore cannot be trivially combined to obtain a larger set. The final aim of our work is the definition and implementation of a platform that integrates datasets of inertial signals in order to make available to the scientific community large datasets of homogeneous signals, enriched, when possible, with context information (e.g., characteristics of the subjects and device position). The main focus of our platform is to emphasise data quality, which is essential for training efficient models.
Improving Out-of-distribution Human Activity Recognition via IMU-Video Cross-modal Representation Learning
Department of Computer Science & Engineering University of Minnesota（计算机科学与工程系明尼苏达大学）；Department of Mechanical Engineering University of Minnesota（机械工程系明尼苏达大学）；Department of Neurosurgery University of Minnesota（神经外科系明尼苏达大学）
MARS: Mixed Virtual and Real Wearable Sensors for Human Activity Recognition with Multi-Domain Deep Learning Model
Shanghai Jiao Tong University（上海交通大学）
随着物联网（IoT）的快速发展，使用可穿戴惯性测量单元（IMU）的人体活动识别（HAR）成为许多研究领域的一项有前途的技术。最近，基于深度学习的方法为理解和执行HAR系统中的复杂数据的分析铺平了新的道路。然而，这些方法的性能主要取决于所收集数据的质量和数量。在本文中，我们创新性地提出了建立一个基于虚拟IMU的大型数据库，然后通过引入一个由三个技术部分组成的多域深度学习框架来解决技术问题。在第一部分中，我们提出了学习的单帧人类活动的噪声IMU数据与混合卷积神经网络（CNN）在半监督的形式。第二部分根据不确定性感知一致性原则对提取的数据特征进行融合，通过对特征重要性进行加权来降低不确定性。最后一部分基于最新发布的运动捕捉存档数据集（Archive of Motion Capture as Surface Practice，AMASS）进行迁移学习，该数据集包含丰富的合成人体姿态，增强了训练数据集的多样性，有利于该方法的训练和特征迁移过程。在实际的深惯性波（DIP）数据集上，验证了该方法的有效性。实验结果表明，所提出的方法可以令人惊讶地收敛在几个迭代和优于所有竞争的方法。
Multimodal video and IMU kinematic dataset on daily life activities using affordable devices (VIDIMU)
University of Valladolid（巴利亚多利德大学）；University of Applied Sciences and Arts Western Switzerland (HES-SO) Valais-Wallis（瑞士西部应用科学与艺术大学 (HES-SO) 瓦莱-沃利斯分校）；University of Geneva（日内瓦大学）
A Deep Learning Method for Complex Human Activity Recognition Using Virtual Wearable Sensors
Shanghai Jiao Tong University（上海交通大学）；School of Electrical Information and Electrical Engineering（电子信息与电气工程学院）；Shanghai Key Laboratory of Navigation and Location-based Services（上海市导航与位置服务重点实验室）
COMODO: Cross-Modal Video-to-IMU Distillation for Efficient Egocentric Human Activity Recognition
The University of New South Wales（新南威尔士大学）；King Mongkut's University of Technology North Bangkok（科技技术北巴吞蓬大学）；The Hong Kong University of Science（香港科学大学）
Deep Adversarial Learning with Activity-Based User Discrimination Task for Human Activity Recognition
AASS, Örebro University（厄勒布鲁大学AASS研究中心）；Faculty of Information Science and Electrical Engineering, Kyushu University（九州大学情报科学与电气工程学院）；ETSIDI, Universidad Politéctina de Madrid（马德里理工大学高等航空工程技术学院）
本文提出含新型基于活动的用户判别任务的对抗深度学习框架，以缓解 HAR 中的人际差异，并在三个数据集的 LOOCV 基准上取得优于以往方法和任务的分类效果。
A comparative study on wearables and single-camera video for upper-limb out-of-thelab activity recognition with different deep learning architectures
University of Valladolid（巴利亚多利德大学）；University of Geneva（日内瓦大学）；University of Applied Sciences Western Switzerland (HES-SO) Valais-Wallis（瑞士西部应用科学与艺术大学（HES-SO）瓦莱-沃利斯）
Sensor Data Augmentation from Skeleton Pose Sequences for Improving Human Activity Recognition
Saarland University（萨尔大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；RPTU Kaiserslautern-Landau（凯撒斯劳滕-兰道莱茵-普法尔茨技术大学）；Seoul National University of Science and Technology（首尔科学技术大学）
Hybrid CNN-Dilated Self-attention Model Using Inertial and Body-Area Electrostatic Sensing for Gym Workout Recognition, Counting, and User Authentification
Human Activity Recognition Based on Electrocardiogram Data Only
Department of Computer Science and Engineering, University of North Texas（计算机科学与工程系，北卡罗来纳州立大学）；Faculty of Computer Science, Technische Universität Dresden（计算机科学系，德累斯顿技术大学）
