The DOI matches its Crossref record; 32 of the 44 references it cites were found in a registry or an index.
Contrastive Self-supervised Learning for Sensor-based Human Activity Recognition
Abstract
Deep Learning models, applied to a sensor-based Human Activity Recognition task, usually require vast amounts of annotated time-series data to extract robust features. However, annotating signals coming from wearable sensors can be a tedious and, often, not so intuitive process, that requires specialized tools and predefined scenarios, making it an expensive and time-consuming task. This paper combines one of the most recent advances in Self-Supervised Leaning (SSL), namely a SimCLR framework, with a powerful transformer-based encoder to introduce a Contrastive Self-supervised learning approach to Sensor-based Human Activity Recognition (CSSHAR) that learns feature representations from unlabeled sensory data. Extensive experiments conducted on three widely used public datasets have shown that the proposed method outperforms recent SSL models. Moreover, CSSHAR is capable of extracting more robust features than the identical supervised transformer when transferring knowledge from one dataset to another as well as when very limited amounts of annotated data are available.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“For instance, CSSHAR [34] adoptd a SimCLR-based framework with a CNN–Transformer encoder. Its model complexity is relatively high (9.3 M, 5.4 M, and 6.6 M parameters on the three datasets), whereas our method uses a ResNet encoder with only 481K parameters, resulting in significantly lower computational and energy demands—making it more suitable for edge-device deployment.”
From Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach (2025) · cites this paper as [34]
In the citing paper
“For instance, CSSHAR [34] adoptd a SimCLR-based framework with a CNN–Transformer encoder. Its model complexity is relatively high (9.3 M, 5.4 M, and 6.6 M parameters on the three datasets), whereas our method uses a ResNet encoder with only 481K parameters, resulting in significantly lower computational and energy demands—making it more suitable for edge-device deployment.”
From Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach (2025) · cites this paper as [34]
In the citing paper
“Other studies proposed generative methods [28, 29, 30] and demonstrated competitive performances.”
From Comparing self-supervised learning techniques for wearable human activity recognition (2025) · cites this paper as [29]
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
(2014) · Cited by 33,419
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
(2010) · International Conference on Machine Learning · Cited by 13,995
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. A., Guo, Z. D., Azar, M. G., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.07733 · Cited by 3,846
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · cited 1×
“While plenty of modern deep learning methods have been used for sensor-based HAR in a supervised manner [24, 5, 15, 28, 26, 11, 13], only a few works have been focused on self-supervised learning.”
MethodTian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997
Cited by
Xiao, Z.-W., Tong, H., Qu, R., Xing, H.-L., Luo, S., Zhu, Z., Song, F., & Feng, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3344294 · Cited by 111
“A BBREVIATIONS : 1) CapMatch With Different t KD Values: t KD is a temperature coefficient to scale the features of the intermediate layers, which facilitates the knowledge flow in the intermediate layers.”
InfluentialSelf-Supervised Contrastive Learning for Medical Time Series: A Systematic Review
Liu, Z., Alavi, A., Li, M., & Zhang, X. (2023) · Sensors · doi:10.3390/s23094221 · Cited by 90
“Similarly, bringing the idea to time series data, an intuitive pretext task is to predict whether the input sequence is permuted or not [87].”
BackgroundCOCOA: Cross Modality Contrastive Learning for Sensor Data
Deldari, S., Xue, H., Saeed, A., Smith, D. V., & Salim, F. D. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3550316 · Cited by 92
“CSSHAR(2021)[45] No NT-Xent[12] Augmentation HAR -(2020)[13] No Info-NCE Augmentation Biosignals (EEG, ECG) TCN(2020) [78] No Triplet Loss temporal General time-series TS-CP2(2020) [18] No Info-NCE temporal General time-series CPC(HAR)(2021) [36] No Info-NCE temporal HAR CPC(EEG)(2021)[8] No Info-NCE temporal EEG sign…”
BackgroundMethodYin, Y., Xie, L., Jiang, Z., Xiao, F., Cao, J., & Lu, S. (2024) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2024.3357591 · Cited by 108
Sensor Data Augmentation by Resampling in Contrastive Learning for Human Activity Recognition
Wang, J., Zhu, T., Gan, J., Chen, L., Ning, H., & Wan, Y. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3214198 · Cited by 83
Metadata
- Authors
- Khaertdinov, B., Ghaleb, E., & Asteriadis, S.
- Affiliations
- Maastricht University (NL)
- Venue
- 2021 IEEE International Joint Conference on Biometrics (IJCB)
- Publisher
- IEEE
- Published
- 2021-08-04
- Pages
- 1-8
- OpenAlex
- W3184978184
- Cited by
- 95
- References
- 44
- Citations by year
- 2026: 9 · 2025: 24 · 2024: 26 · 2023: 22 · 2022: 13 · 2021: 1
- FWCI
- 4.81
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Joint Conference on Biometrics (IJCB) (publishedVersion)
- Research Publications (Maastricht University) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Keywords
- human activity recognition, wearable sensors, self-supervised learning, contrastive learning, SimCLR, Transformer encoder, unlabeled data, feature representation learning, domain transfer, limited labeled data
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Contrastive Self-supervised Learning for Sensor-based Human Activity Recognition. https://app.cochat.ai/papers/10.1109/ijcb52358.2021.9484410
- The paper
- Khaertdinov, B., Ghaleb, E., & Asteriadis, S. (2021). Contrastive Self-supervised Learning for Sensor-based Human Activity Recognition. 2021 IEEE International Joint Conference on Biometrics (IJCB). https://doi.org/10.1109/ijcb52358.2021.9484410
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.