mlsanityData to 14 Oct 2026

Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Data

arXiv 2206.02909 ↗First posted 6 Jun 2022eess.SP cs.AI cs.LGcited by 75

Not on the map. Why?

Abstract (arXiv)

Advances in deep learning for human activity recognition have been relatively limited due to the lack of large labelled datasets. In this study, we leverage self-supervised learning techniques on the UK-Biobank activity tracker dataset--the largest of its kind to date--containing more than 700,000 person-days of unlabelled wearable sensor data. Our resulting activity recognition model consistently outperformed strong baselines across seven benchmark datasets, with an F1 relative improvement of 2.5%-100% (median 18.4%), the largest improvements occurring in the smaller datasets. In contrast to previous studies, our results generalise across external datasets, devices, and environments. Our open-source model will help researchers and developers to build customisable and generalisable activity classifiers with high performance.

Key facts. Cited by 75 papers in the map (data through 14 Oct 2026). Builds on 29 of its 78 references that are in the map. First posted on arXiv 6 Jun 2022.

Builds on

29 of 78 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  7. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  8. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  9. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  10. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  11. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  12. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
17 more
  1. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  2. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,492
  3. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  4. 2016Colorful Image Colorizationcited by 1,114
  5. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,066
  6. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  7. 2017Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networkscited by 131
  8. 2019Multi-task Self-Supervised Learning for Human Activity Detectioncited by 102
  9. 2016Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearablescited by 94
  10. 2020Exploring Contrastive Learning in Human Activity Recognition for Healthcarecited by 75
  11. 2019Towards Best Practice in Explaining Neural Network Decisions with LRPcited by 70
  12. 2022Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?cited by 67
  13. 2022Assessing the State of Self-Supervised Human Activity Recognition using Wearablescited by 65
  14. 2020Contrastive Predictive Coding for Human Activity Recognitioncited by 55
  15. 2021SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Datacited by 31
  16. 2021Evaluating Contrastive Learning on Wearable Timeseries for Downstream Clinical Outcomescited by 8
  17. 2021Interpretable Deep Learning for the Remote Characterisation of Ambulation in Multiple Sclerosis using Smartphonescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 6; 2024: 15; 2025: 25; 2026: 26.

75 papers.

Sort:

By area:

  1. 2024PaPaGei: Open Foundation Models for Optical Physiological Signalscited by 69
  2. 2024Scaling Wearable Foundation Modelscited by 63
  3. 2025SensorLM: Learning the Language of Wearable Sensorscited by 49
  4. 2023The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Modelscited by 34
  5. 2024Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signalscited by 32
  6. 2024UniMTS: Unified Pre-training for Motion Time Seriescited by 26
  7. 2025LSM-2: Learning from Incomplete Wearable Sensor Datacited by 23
  8. 2024RelCon: Relative Contrastive Learning for a Motion Foundation Model for Wearable Datacited by 20
  9. 2025HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Seriescited by 19
  10. 2024Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognitioncited by 18
  11. 2025Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictionscited by 18
  12. 2024Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Datacited by 17
38 more
  1. 2024Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Taskcited by 15
  2. 2024Large Language Models are Zero-Shot Recognizers for Activities of Daily Livingcited by 13
  3. 2026OSF: On Pre-training and Scaling of Sleep Foundation Modelscited by 12
  4. 2024A Survey on Multimodal Wearable Sensor-based Human Action Recognitioncited by 10
  5. 2024PRIMUS: Pretraining IMU Encoders with Multimodal Self-Supervisioncited by 10
  6. 2023On convex decision regions in deep network representationscited by 7
  7. 2025Towards Generalizable Human Activity Recognition: A Surveycited by 6
  8. 2025Foundation Models for CPS-IoT: Opportunities and Challengescited by 5
  9. 2025Scaling laws in wearable human activity recognitioncited by 4
  10. 2025WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatchcited by 4
  11. 2023A benchmark for computational analysis of animal behavior, using animal-borne tagscited by 3
  12. 2023ConvBoost: Boosting ConvNets for Sensor-based Activity Recognitioncited by 3
  13. 2025Graph-Based Physics-Guided Urban PM2.5 Air Quality Imputation with Constrained Monitoring Datacited by 3
  14. 2025High-Performance Self-Supervised Learning by Joint Training of Flow Matchingcited by 3
  15. 2026Inertia-1: An Open Exploration of Wearable Motion Foundation Modelscited by 3
  16. 2022IMG2IMU: Translating Knowledge from Large-Scale Images to IMU Sensing Applicationscited by 2
  17. 2022LEAVES: Learning Views for Time-Series Biobehavioral Data in Contrastive Learningcited by 2
  18. 2023Human Activity Recognition Using Self-Supervised Representations of Wearable Datacited by 2
  19. 2023Don't freeze: Finetune encoders for better Self-Supervised HARcited by 2
  20. 2024CUDLE: Learning Under Label Scarcity to Detect Cannabis Use in Uncontrolled Environmentscited by 2
  21. 2025Evidence for Phenotype-Driven Disparities in Freezing of Gait Detection and Approaches to Bias Mitigationcited by 2
  22. 2025SlotFM: A Motion Foundation Model with Slot Attention for Diverse Downstream Taskscited by 2
  23. 2026TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoningcited by 2
  24. 2026Bio-Inspired Self-Supervised Learning for Wrist-worn Accelerometer Datacited by 2
  25. 2026BenchHAR: Benchmarking Self-Supervised Learning for Generalizable Sensor-based Activity Recognitioncited by 2
  26. 2022Simple Yet Surprisingly Effective Training Strategies for LSTMs in Sensor-Based Human Activity Recognitioncited by 1
  27. 2024SelfReplay: Adapting Self-Supervised Sensory Models via Adaptive Meta-Task Replaycited by 1
  28. 2025PIM: Physics-Informed Multi-task Pre-training for Improving Inertial Sensor-Based Human Activity Recognitioncited by 1
  29. 2025CLAD-Net: Continual Activity Recognition in Multi-Sensor Wearable Systemscited by 1
  30. 2025Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approachescited by 1
  31. 2025On-device Large Multi-modal Agent for Human Activity Recognitioncited by 1
  32. 2026Learning Longitudinal Health Representations from EHR and Wearable Datacited by 1
  33. 2026Prediction of Challenging Behaviors Associated with Profound Autism in a Classroom Setting Using Wearable Sensorscited by 1
  34. 2026Next-Token Prediction Learns Generalisable Representations of Sleep Physiologycited by 1
  35. 2026Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detectioncited by 1
  36. 2026Joint-Embedding Predictive Architecture for Sensor-based Activity Recognitioncited by 1
  37. 2024Detecting Daily Living Gait Amid Huntington's Disease Chorea using a Foundation Deep Learning Modelcited by 0
  38. 2024Automatic Self-supervised Learning for Social Recommendationscited by 0

50 most cited of 75 All 75 (JSON)