# Human Activity Recognition on wrist-worn accelerometers using self-supervised neural networks

arXiv: https://arxiv.org/abs/2112.12272 · HTML: https://mlsanity.com/paper/2112.12272/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 22 Dec 2021.

## Builds on (most cited first, 6 of 6)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [Look, Listen and Learn](https://mlsanity.com/paper/1705.08168/) (2017)
- [Stratified Transfer Learning for Cross-domain Activity Recognition](https://mlsanity.com/paper/1801.00820/) (2017)
- [Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision](https://mlsanity.com/paper/1911.05894/) (2019)
- [Are Accelerometers for Activity Recognition a Dead-end?](https://mlsanity.com/paper/2001.08111/) (2020)

## Built on by (most cited first, 1 of 1)

- [ActiNet: An Open-Source Tool for Activity Intensity Classification of Wrist-Worn Accelerometry Using Self-Supervised Deep Learning](https://mlsanity.com/paper/2510.01712/) (2025)

## Abstract (arXiv)

Measures of Activity of Daily Living (ADL) are an important indicator of overall health but difficult to measure in-clinic. Automated and accurate human activity recognition (HAR) using wrist-worn accelerometers enables practical and cost efficient remote monitoring of ADL. Key obstacles in developing high quality HAR is the lack of large labeled datasets and the performance loss when applying models trained on small curated datasets to the continuous stream of heterogeneous data in real-life. In this work we design a self-supervised learning paradigm to create a robust representation of accelerometer data that can generalize across devices and subjects. We demonstrate that this representation can separate activities of daily living and achieve strong HAR accuracy (on multiple benchmark datasets) using very few labels. We also propose a segmentation algorithm which can identify segments of salient activity and boost HAR accuracy on continuous real-life data.