Temporal Distance Based Self-Supervised Learning for Human Activity Recognition
The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
Self-supervised learning provides a scalable method for acquiring representations from unlabelled data, a capability that is essential in domains such as sensor-based Human Activity Recognition, where the labelling of signals can be prohibitively expensive. This paper introduces Temporal Distance-based SelfSupervised Learning (TD-SSL), a novel framework that exploits the temporal distance of accelerometer sequences to build contrastive data pairs used to construct a pretrained backbone for human activity recognition models. The method is based on the hypothesis that in a continuous sensor stream, temporally adjacent samples likely correspond to the same activity, while distant ones represent distinct actions. A study was conducted in which three distinct network architectures - convolutional, DenseNet-like, and multi-head attention neural networks - were evaluated on four publicly available datasets. The experimental evaluations demonstrate that TD-SSL consistently achieves the performance of supervised benchmarks, thereby confirming learning transferability. Furthermore, in scenarios where labeled data is scarce, it surpasses the supervised approach by more than 10 percentage points, significantly reducing the need for manual annotation in sensor-based human activity recognition.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260 · cited 1×
“In particular, it has demonstrated great success in domains like computer vision [7], speech [8], and natural language processing [9], but its application to sensor-based HAR remains somewhat under-explored to this day.”
Doherty, A., Jackson, D., Hammerla, N., Plötz, T., Olivier, P., Granat, M. H., White, T., van Hees, V. T., Trenell, M. I., Owen, C. G., et al. (2017) · PLOS ONE · doi:10.1371/journal.pone.0169649 · Cited by 1,250
Deep Learning for Sensor-based Human Activity Recognition
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2022) · ACM Computing Surveys · doi:10.1145/3447744 · Cited by 690
Window Size Impact in Human Activity Recognition
Banos, O., Galvez, J.-M., Damas, M., Pomares, H., & Rojas, I. (2014) · Sensors · doi:10.3390/s140406474 · Cited by 648
Multi-task Self-Supervised Learning for Human Activity Detection
Saeed, A., Ozcelebi, T., & Lukkien, J. (2019) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3328932 · Cited by 346 · cited 1×
“Saeed et al. [11] proposed a general approach to self-supervised learning by applying various transformations to the signal, namely noise, scaling, rotation, negation, horizontal flipping, permutation time-warping and channel shuffling , and training a network with a common feature extractor…”
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2020) · arXiv · doi:10.48550/arxiv.2001.07416 · Cited by 314
The MobiAct Dataset: Recognition of Activities of Daily Living using Smartphones
Vavoulas, G., Chatzaki, C., Malliotakis, T., Pediaditis, M., & Tsiknakis, M. (2016) · Proceedings of the International Conference on Information and Communication Technologies for Ageing Well and e-Health · doi:10.5220/0005792401430151 · Cited by 301
Mobile sensor data anonymization
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2019) · Proceedings of the International Conference on Internet of Things Design and Implementation · doi:10.1145/3302505.3310068 · Cited by 298 · cited 1×
“The pretraining phase was conducted using the CAP-TURE24 dataset [3], while to evaluate the transfer learning capability, we used four different publicly available datasets, namely, MotionSense [23], mobiAct [24], watchHAR [25], and UCI-HAR [26].”
Contrastive Predictive Coding for Human Activity Recognition
Haresamudram, H., Essa, I., & Plötz, T. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3463506 · Cited by 150
Research works printed but not linked: 4
- Mikolov, 2013, Efficient estimation of word representations in vector space, arXiv preprint
- 10.3390/technologies9010002 · DOI · Paper page
- Alevizaki, 2022, watchhar: A smartwatch imu dataset for activities of daily living
- Irvine, 2025, Human activity recognition using smartphones
Cited by
Still being checked.
Metadata
- Authors
- Bigelli, L., Contoli, C., Kania, N., & Lattanzi, E.
- Affiliations
- University of Urbino (IT)
- Venue
- 2025 Sixth International Conference on Intelligent Data Science Technologies and Applications (IDSTA)
- Publisher
- IEEE
- Published
- 2025-09-01
- Pages
- 73-80
- OpenAlex
- W7093297095
- Cited by
- 0
- References
- 23
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Intelligent Data Science Technologies and Applications (IDSTA) (publishedVersion)
- CINECA IRIS Institutional Research information system (University of Urbino) (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
- self-supervised learning, human activity recognition, temporal distance, contrastive learning, sensor-based activity recognition, multi-head attention, DenseNet, convolutional neural networks, transfer learning, 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: Temporal Distance Based Self-Supervised Learning for Human Activity Recognition. https://app.cochat.ai/papers/10.1109/idsta66210.2025.11202839
- The paper
- Bigelli, L., Contoli, C., Kania, N., & Lattanzi, E. (2025). Temporal Distance Based Self-Supervised Learning for Human Activity Recognition. 2025 Sixth International Conference on Intelligent Data Science Technologies and Applications (IDSTA). https://doi.org/10.1109/idsta66210.2025.11202839
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.