Developing human activity recognition (HAR) systems for smart homes is not
straightforward due to varied layouts of the homes and their personalized
settings, as well as idiosyncratic behaviors of residents. As such,
off-the-shelf HAR systems are effective in limited capacity for an individual
home, and HAR systems often need to be derived "from scratch", which comes with
substantial efforts and often is burdensome to the resident. Previous work has
successfully targeted the initial phase. At the end of this initial phase, we
identify seed points. We build on bootstrapped HAR systems and introduce an
effective updating and extension procedure for continuous improvement of HAR
systems with the aim of keeping up with ever changing life circumstances. Our
method makes use of the seed points identified at the end of the initial
bootstrapping phase. A contrastive learning framework is trained using these
seed points and labels obtained for the same. This model is then used to
improve the segmentation accuracy of the identified prominent activities.
Improvements in the activity recognition system through this procedure help
model the majority of the routine activities in the smart home. We demonstrate
the effectiveness of our procedure through experiments on the CASAS datasets
that show the practical value of our approach.

通过使用种子点和对比学习框架，本研究提出了一种有效的方法来改善智能家居中的活动识别系统，以更准确地识别主要活动。

维护需求：更新和扩展用于智能家居的引导式人体活动识别系统

Maintenance Required: Updating and Extending Bootstrapped Human Activity  Recognition Systems for Smart Homes

Human Activity Recognition (HAR) systems have been extensively studied by the
vision and ubiquitous computing communities due to their practical applications
in daily life, such as smart homes, surveillance, and health monitoring.
Typically, this process is supervised in nature and the development of such
systems requires access to large quantities of annotated data.
However, the higher costs and challenges associated with obtaining good
quality annotations have rendered the application of self-supervised methods an
attractive option and contrastive learning comprises one such method.
However, a major component of successful contrastive learning is the
selection of good positive and negative samples.
Although positive samples are directly obtainable, sampling good negative
samples remain a challenge.
As human activities can be recorded by several modalities like camera and IMU
sensors, we propose a hard negative sampling method for multimodal HAR with a
hard negative sampling loss for skeleton and IMU data pairs.
We exploit hard negatives that have different labels from the anchor but are
projected nearby in the latent space using an adjustable concentration
parameter.
Through extensive experiments on two benchmark datasets: UTD-MHAD and MMAct,
we demonstrate the robustness of our approach forlearning strong feature
representation for HAR tasks, and on the limited data setting.
We further show that our model outperforms all other state-of-the-art methods
for UTD-MHAD dataset, and self-supervised methods for MMAct: Cross session,
even when uni-modal data are used during downstream activity recognition.

人类活动识别（HAR）是一个广泛研究的课题，其中对于多模态 HAR，采用一种硬负采样方法以及对骨骼和 IMU 数据对的硬负采样损失进行学习，能够提供强大的特征表征，用于活动识别。