Unsupervised Sensor-Based Human Activity Recognition via Contrastive Learning of Representation
- 1 October 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (20) , 47603-47620
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62373194)
This publication has 57 references indexed in Scilit:
- Long kernel distillation in human activity recognitionKnowledge-Based Systems, 2025
- EnsCLR: Unsupervised skeleton-based action recognition via ensemble contrastive learning of representationComputer Vision and Image Understanding, 2024
- Wearable Sensor-Based Human Activity Recognition for Worker Safety in Manufacturing Line2023
- Deep-HAR: an ensemble deep learning model for recognizing the simple, complex, and heterogeneous human activitiesMultimedia Tools and Applications, 2023
- Cross-View Nearest Neighbor Contrastive Learning of Human Skeleton Representation2023
- Deep Learning Models for Real-time Human Activity Recognition with SmartphonesMobile Networks and Applications, 2019
- Examining sensor-based physical activity recognition and monitoring for healthcare using Internet of Things: A systematic reviewJournal of Biomedical Informatics, 2018
- Real-time human activity recognition from accelerometer data using Convolutional Neural NetworksApplied Soft Computing, 2018
- Human activity recognition with smartphone sensors using deep learning neural networksExpert Systems with Applications, 2016
- Activity Recognition from User-Annotated Acceleration Data2004