Comparing self-supervised learning techniques for wearable human activity recognition
Open accessThe DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index; 1 of the 30 sources its claims cite were checked for support.
Abstract
Human Activity Recognition (HAR) based on the sensors of mobile/wearable devices aims to detect the physical activities performed by humans in their daily lives. Although supervised learning methods are the most effective in this task, their effectiveness is constrained to using a large amount of labeled data during training. While collecting raw unlabeled data can be relatively easy, annotating data is challenging due to costs, intrusiveness, and time constraints. To address these challenges, this paper explores alternative approaches for accurate HAR using a limited amount of labeled data. In particular, we have adapted recent Self-Supervised Learning (SSL) algorithms to the HAR domain and compared their effectiveness. We investigate three state-of-the-art SSL techniques of different families: contrastive, generative, and predictive. Additionally, we evaluate the impact of the underlying neural network on the recognition rate by comparing state-of-the-art CNN and transformer architectures. Our results show that a Masked Auto Encoder approach significantly outperforms other SSL approaches, including SimCLR, commonly considered one of the best-performing SSL methods in the HAR domain. The code and the pre-trained SSL models are publicly available for further research and development.
Overview
CoChat Summary
## TL;DR
The paper compares three SSL approaches for wearable HAR—SimCLR, MAE, and data2vec—across CNN (iSPLInception) and transformer (HART) backbones using a Leave-One-Dataset-Out benchmark. MAE is the most robust method, especially in the frozen-feature-extractor setting and in low-label regimes, while SimCLR performs worst overall.
## Key findings
- With the feature extractor frozen, MAE outperformed the other SSL methods and the supervised baseline on average: 80.90 ± 10.88 (iSPL) and 82.56 ± 11.38 (HART), versus supervised 65.74 ± 16.56 and 74.95 ± 15.92.
- In the frozen, dataset-level results, MAE was best on every dataset reported; for example, on HHAR it reached 66.11 ± 1.05 (iSPL) and 66.64 ± 1.61 (HART), and on UCI 92.17 ± 0.83 (iSPL) and 93.40 ± 0.38 (HART).
- In the unfrozen setting with full training data, there was no clear winner; performances were very close, with all methods reaching about the same recognition rates for a given architecture.
- In scarce-label experiments, MAE was consistently strongest overall and achieved above 60% F1 with only 10 samples per class in the frozen setting; SimCLR performed very poorly, especially on RealWorld.
## Methods
- The study adapts and compares three SSL families for HAR: SimCLR (contrastive), MAE (generative/masking), and data2vec (predictive), each paired with two architectures: iSPLInception and HART.
- Evaluation uses Leave-One-Dataset-Out (LODO) across six public inertial-sensor datasets: HHAR, MobiAct, MotionSense, RealWorld, UCI, and PAMAP2; data were downsampled to 50 Hz, windowed into 128-sample segments with 50% overlap, yielding 147 subjects, 10 activities, 213,289 samples (about 151 hours), and 12 devices.
- Main analysis: pretraining for 300 epochs with batch size 128, then fine-tuning for 100 epochs with batch size 64; performance is reported using macro F1, averaged over 5 random runs, under both frozen and unfrozen feature-extractor settings and across label-scarcity scenarios from 1 to 100 samples per class.
## Limitations
- The paper states that the study was limited to three SSL techniques and two models, and that it was conducted only as offline experiments; behavior in real-world settings remains to be evaluated.
- The authors note that the available HAR datasets are still much smaller and less diverse than those in vision or text, even though LODO helps mitigate limited data.
- Evident from the text: the label-scarcity experiments are reported only on RealWorld and MotionSense for presentation purposes, even though complete results exist in the repository.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
1 Valid · 3 Not valid · 17 Not checked · 75 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The majority of these works have focused on contrastive approaches [23, 24, 25, 26, 27].”
What the sources say
- Partly supportedcites [23] Haresamudram, H., Essa, I., Plötz, T.: Investigating enhancements to contrastive predictive coding for human activity recognition. In: 2023 IEEE International Conference on Pervasive Computing and Communications (PerCom), pp. 232–241 (2023). IEEE sourceExperimental — accuracy not yet measured
Our copy's Related Work (II) and Introduction (I) catalogue the SSL HAR literature and much of it is contrastive — SimCLR [24], [26], CPC [21], CPC-based change point detection [25], and the multi-sensor ColloSSL [35] / COCOA [36] — which lends direction to the claim. However, no passage states or implies that the majority of SSL work in HAR is contrastive: the same sections give equal standing to non-contrastive approaches (Multi-task self-supervision [19], Masked Reconstruction [20], Autoencoders [23], [29]) and explicitly note that SimSiam and BYOL 'are also siamese methods, albeit do not contrast the two views' (II). The Introduction's own summary list of methods for wearables contains only two contrastive entries out of four. So the source supports 'contrastive approaches are prominent in SSL for HAR' but not the quantitative 'majority' assertion attributed to it. (LLM, conf=0.68)
- Not checked yetcites [24] He, K., Chen, X., Xie, S., Li, Y., Dollár, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000–16009 (2022) source
- Not checked yetcites [25] Hernandez, N., Lundström, J., Favela, J., McChesney, I., Arnrich, B.: Literature review on transfer learning for human activity recognition using mobile and wearable devices with environmental technology. SN Comput. Sci. 1, 1–16 (2020) source
- Not checked yetcites [26] Ignatov, A.: Real-time human activity recognition from accelerometer data using convolutional neural networks. Appl. Soft Comput. 62 (2018) source
- Not checked yetcites [27] Jain, Y., Tang, C.I., Min, C., Kawsar, F., Mathur, A.: Collossl: Collaborative self-supervised learning for human activity recognition. In: Proc. of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 6(1) (2022) source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The findings indicate that MAE emerges as the most robust technique for the domain, surpassing all other approaches, including supervised pre-training methods.”
hedgedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our results show that a Masked Auto Encoder (MAE) approach significantly outperforms other SSL approaches, including SimCLR, commonly considered one of the best-performing SSL methods in the HAR domain.”
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Differences in performances are generally below a 1% margin between the best and performing techniques on both architectures.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the data-scarce environment, we saw that self-supervised pre-training allowed the model to perform better in extremely low sample ranges when compared to starting from random, and results converged to equivalent performance with more training data.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
50 more claims
Create a free account to see all 96 claims and to verify the 29 references still open.
- It may state two separate claims as one. 19
- Probably not a substantial claim. 25
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“In the following, we describe the six datasets (HHAR, MobiAct, MotionSense, Realworld, UCI, and PAMAP2) employed in this study.”
“We gathered seven datasets, each possessing unique traits that distinguish them from one another.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“During the fine-tuning phase, we performed 100 epochs with a batch size of 64 on the left-out datasets.”
“the training process is constrained (from 200 epochs to only 50 epochs).”
Citations
Cites
Masked Autoencoders Are Scalable Vision Learners
He, K., Chen, X., Xie, S., Li, Y., Dollar, P., & Girshick, R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01553 · Cited by 8,489 · cited 6×
“However, the complete results on all seven datasets are also given in the shared code repository.”
InfluentialBootstrap 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
Exploring Simple Siamese Representation Learning
Chen, X., & He, K. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01549 · Cited by 3,725 · cited 1×
“Furthermore, unlike other siamese methods, such as BYOL (Grill et al. 2020) or SimSiam (Chen and He 2021), which employ additional components such as projection heads in the student model to mitigate collapse, Data2Vec does not utilize such mechanisms, making it more susceptible to this issue.”
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
A survey on semi-supervised learning
van Engelen, J. E., & Hoos, H. H. (2020) · Machine Learning · doi:10.1007/s10994-019-05855-6 · Cited by 2,666 · cited 1×
“For this purpose, Self-Supervised Learning (SSL) meth-ods (Van Engelen and Hoos 2020) can prove to be highly effective.”
A Survey on Human Activity Recognition using Wearable Sensors
Lara, O. D., & Labrador, M. A. (2013) · IEEE Communications Surveys & Tutorials · doi:10.1109/surv.2012.110112.00192 · Cited by 2,662
Deep learning for sensor-based activity recognition: A survey
Wang, J., Chen, Y., Hao, S., Peng, X., & Hu, L. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.02.010 · Cited by 2,014 · cited 1×
“In this case, the most effective approaches rely on deep learning, where high recognition rates are achieved through the use of supervised learning techniques (Wang et al. 2019).”
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Gu, A., & Dao, T. (2023) · arXiv · doi:10.48550/arxiv.2312.00752 · Cited by 1,579
Introducing a New Benchmarked Dataset for Activity Monitoring
Reiss, A., & Stricker, D. (2012) · 2012 16th International Symposium on Wearable Computers · doi:10.1109/iswc.2012.13 · Cited by 1,456 · cited 4×
“This section provides an overview of the datasets used and the evaluation strategies employed to assess the performance of the pre-trained models obtained through various SSL techniques and architectures.”
InfluentialDoherty, 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 · cited 2×
“Despite recent advancements (Chan Chang et al. 2021; Doherty et al. 2017), there have yet to be publicly available Gold-standard datasets that are expansive and inclusive of diverse devices, positions, users, and sensors.”
Sensor-Based Activity Recognition
Chen, L., Hoey, J., Nugent, C. D., Cook, D. J., & Yu, Z. (2012) · IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) · doi:10.1109/tsmcc.2012.2198883 · Cited by 1,074 · cited 1×
“Human activity recognition (HAR) aims to recognize human actions automatically using sensor data (Chen et al. 2012).”
Pre-trained models: Past, present and future
Han, X., Zhang, Z., Ding, N., Gu, Y., Liu, X., Huo, Y., Qiu, J., Yao, Y., Zhang, A., Zhang, L., et al. (2021) · AI Open · doi:10.1016/j.aiopen.2021.08.002 · Cited by 994 · cited 1×
“We propose that these problems can be mitigated by promoting the use of robust pre-trained models (Han et al. 2021), a foundational aspect of transfer learning in which knowledge gained while solving one problem is applied to a different but related problem.”
Real-time human activity recognition from accelerometer data using Convolutional Neural Networks
Ignatov, A. (2018) · Applied Soft Computing · doi:10.1016/j.asoc.2017.09.027 · Cited by 814 · cited 1×
“Next, the data were segmented into windows which contain 128 samples (equivalent to 2.56 seconds) with a 50% overlap for the accelerometer and gyroscope readings across all six channels, as past studies have done (Ignatov 2018).”
InfluentialStisen, A., Blunck, H., Bhattacharya, S., Prentow, T. S., Kjærgaard, M. B., Dey, A., Sonne, T., & Jensen, M. M. (2015) · Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/2809695.2809718 · Cited by 714 · cited 2×
“The Heterogeneity Human Activity Recognition (HHAR) dataset (Stisen et al. 2015) showcases a diverse range of smartphone and smartwatch models, adding to our variability.”
Time-Series Representation Learning via Temporal and Contextual Contrasting
Eldele, E., Ragab, M., Chen, Z., Wu, M., Kwoh, C. K., Li, X., & Guan, C. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/324 · Cited by 696 · cited 1×
“(Eldele et al. 2021) While in this work we show that SimCLR leads to the worst results, newer contrastive approaches, like Sta-tioCL (Wu et al. 2024) which leverages weak augmentations, may potentially mitigate the SimCLR’s problems in cross-dataset scenarios.”
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
Assran, M., Duval, Q., Misra, I., Bojanowski, P., Vincent, P., Rabbat, M., LeCun, Y., & Ballas, N. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01499 · Cited by 456 · cited 1×
“Data2vec and the Supervised approach performed very comparatively, often interchanging second and third place in performance.”
Self-Supervised Representation Learning: Introduction, advances, and challenges
Ericsson, L., Gouk, H., Loy, C. C., & Hospedales, T. M. (2022) · IEEE Signal Processing Magazine · doi:10.1109/msp.2021.3134634 · Cited by 433 · cited 1×
“Lastly, the pretext task of predictive approaches involves the prediction of some properties of data samples.”
Self-supervised speech representation learning: A review
Mohamed, A., Lee, H.-Y., Borgholt, L., Havtorn, J. D., Edin, J., Igel, C., Kirchhoff, K., Li, S.-W., Livescu, K., Maaløe, L., et al. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3207050 · Cited by 372 · cited 2×
“1 A selection of SSL publication timelines for HAR and their categories based on arXiv observed that most SSL techniques are contrastive methods, whereas other domains have shown a strong shift toward predictive approaches (Mohamed et al. 2022).”
On-body localization of wearable devices: An investigation of position-aware activity recognition
Sztyler, T., & Stuckenschmidt, H. (2016) · 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom.2016.7456521 · Cited by 369 · cited 2×
“This section provides an overview of the datasets used and the evaluation strategies employed to assess the performance of the pre-trained models obtained through various SSL techniques and architectures.”
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 · cited 1×
“MobiAct (Vavoulas et al. 2016) includes 61 subjects, making it the dataset with the largest number of subjects in our collection.”
Human Activity Recognition Using Inertial Sensors in a Smartphone: An Overview
Sousa Lima, W., Souto, E., El-Khatib, K., Jalali, R., & Gama, J. (2019) · Sensors · doi:10.3390/s19143213 · Cited by 256 · cited 2×
“This section provides an overview of the datasets used and the evaluation strategies employed to assess the performance of the pre-trained models obtained through various SSL techniques and architectures.”
iSPLInception: An Inception-ResNet Deep Learning Architecture for Human Activity Recognition
Ronald, M., Poulose, A., & Han, D. S. (2021) · IEEE Access · doi:10.1109/access.2021.3078184 · Cited by 217 · cited 1×
“1 A selection of SSL publication timelines for HAR and their categories based on arXiv observed that most SSL techniques are contrastive methods, whereas other domains have shown a strong shift toward predictive approaches (Mohamed et al. 2022).”
Exploring semi-supervised and active learning for activity recognition
Stikic, M., Van Laerhoven, K., & Schiele, B. (2008) · 2008 12th IEEE International Symposium on Wearable Computers · doi:10.1109/iswc.2008.4911590 · Cited by 197 · cited 1×
“Semi-supervised learning is another technique to mitigate the scarcity of labeled data, which uses a small amount of labeled data while using a much larger amount of unlabeled data (Stikic et al. 2008).”
Protecting sensory data against sensitive inferences
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2018) · Spiral (Imperial College London) · Cited by 166
Protecting Sensory Data against Sensitive Inferences
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2018) · Proceedings of the 1st Workshop on Privacy by Design in Distributed Systems · doi:10.1145/3195258.3195260 · Cited by 154 · cited 1×
“This section provides an overview of the datasets used and the evaluation strategies employed to assess the performance of the pre-trained models obtained through various SSL techniques and architectures.”
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 · cited 1×
“Other studies proposed generative meth-ods (Varamin et al. 2018; Haresamudram et al. 2020; Zhang et al. 2022) and demonstrated competitive performances.”
Xu, H., Zhou, P., Tan, R., Li, M., & Shen, G. (2021) · Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/3485730.3485937 · Cited by 150 · cited 1×
“1, most of these works have focused on contrastive approaches (Saeed et al. 2020; Khaertdinov et al. 2021; Qian et al. 2022; Wang et al. 2022; Jain et al. 2022; Zhang et al. 2022; Arrotta et al. 2023; Taghanaki et al. 2023; Meng et al. 2023).”
Masked reconstruction based self-supervision for human activity recognition
Haresamudram, H., Beedu, A., Agrawal, V., Grady, P. L., Essa, I., Hoffman, J., & Plötz, T. (2020) · Proceedings of the 2020 International Symposium on Wearable Computers · doi:10.1145/3410531.3414306 · Cited by 146 · cited 1×
“Other studies proposed generative meth-ods (Varamin et al. 2018; Haresamudram et al. 2020; Zhang et al. 2022) and demonstrated competitive performances.”
SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
Tang, C. I., Perez-Pozuelo, I., Spathis, D., Brage, S., Wareham, N., & Mascolo, C. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3448112 · Cited by 140 · cited 1×
“Other well-known semi-supervised approaches are self-learning (Tang et al. 2021), label propagation (Stikic et al. 2009) and co-training (Guan et al. 2007).”
ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition
Jain, Y., Tang, C. I., Min, C., Kawsar, F., & Mathur, A. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3517246 · Cited by 113 · cited 1×
“1, most of these works have focused on contrastive approaches (Saeed et al. 2020; Khaertdinov et al. 2021; Qian et al. 2022; Wang et al. 2022; Jain et al. 2022; Zhang et al. 2022; Arrotta et al. 2023; Taghanaki et al. 2023; Meng et al. 2023).”
Assessing the State of Self-Supervised Human Activity Recognition Using Wearables
Haresamudram, H., Essa, I., & Plötz, T. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3550299 · Cited by 107 · cited 2×
“Recently, Self-Supervised Learning (SSL) has become one of the most popular methods to mitigate the scarcity of labeled data (Haresamudram et al. 2022).”
Federated Self-Supervised Learning of Multisensor Representations for Embedded Intelligence
Saeed, A., Salim, F. D., Ozcelebi, T., & Lukkien, J. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3009358 · Cited by 106 · cited 1×
“While SSL has primarily been explored in Speech, Natural Language Processing and Vision domain, it has recently been applied to sensor-based HAR by several research groups (Haresamudram et al. 2022).”
Activity Recognition Based on Semi-supervised Learning
Guan, D., Yuan, W., Lee, Y.-K., Gavrilov, A., & Lee, S. (2007) · 13th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA 2007) · doi:10.1109/rtcsa.2007.17 · Cited by 104 · cited 1×
“Other well-known semi-supervised approaches are self-learning (Tang et al. 2021), label propagation (Stikic et al. 2009) and co-training (Guan et al. 2007).”
Transformer-based models to deal with heterogeneous environments in Human Activity Recognition
Ek, S., Portet, F., & Lalanda, P. (2023) · Personal and Ubiquitous Computing · doi:10.1007/s00779-023-01776-3 · Cited by 101 · cited 15×
“Finally, in addition to the adaptations performed in this work, we conducted an extensive grid search involving three hyper-parameters for each of the presented SSL methods using HART and iSPL on the HHAR dataset.”
InfluentialSelf-citationContrastive Self-supervised Learning for Sensor-based Human Activity Recognition
Khaertdinov, B., Ghaleb, E., & Asteriadis, S. (2021) · 2021 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb52358.2021.9484410 · Cited by 95 · cited 1×
“For instance, pre-trained Large Language Models like GPT are trained using a pretext task to predict the following word in the text (Ericsson et al. 2022).”
Federated Self-Supervised Learning of Multisensor Representations for Embedded Intelligence
Saeed, A., Salim, F. D., Özçelebi, T., & Lukkien, J. J. (2024) · Figshare · Cited by 92
Presotto, R., Civitarese, G., & Bettini, C. (2022) · Personal and Ubiquitous Computing · doi:10.1007/s00779-022-01688-8 · Cited by 91
Self-citationSensor Data Augmentation by Resampling in Contrastive Learning for Human Activity Recognition
Wang, J., Zhu, T., Gan, J., Chen, L. L., Ning, H., & Wan, Y. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3214198 · Cited by 76
Hernandez-Cruz, N., Lundström, J., Favela, J., McChesney, I., & Arnrich, B. (2020) · SN Computer Science · doi:10.1007/s42979-020-0070-4 · Cited by 69 · cited 1×
“One of these methods is Transfer learning (Hernandez et al. 2020; Pavliuk et al. 2023), which leverages pre-existing models trained on large labeled datasets to mitigate the amount of fine-tuning data required for a new target domain.”
Transfer Learning Approach for Human Activity Recognition Based on Continuous Wavelet Transform
Pavliuk, O., Mishchuk, M., & Strauß, C. (2023) · Algorithms · doi:10.3390/a16020077 · Cited by 69 · cited 1×
“One of these methods is Transfer learning (Hernandez et al. 2020; Pavliuk et al. 2023), which leverages pre-existing models trained on large labeled datasets to mitigate the amount of fine-tuning data required for a new target domain.”
Multi-graph Based Semi-supervised Learning for Activity Recognition
Stikic, M., Larlus, D., & Schiele, B. (2009) · 2009 International Symposium on Wearable Computers · doi:10.1109/iswc.2009.24 · Cited by 68 · cited 1×
“Other well-known semi-supervised approaches are self-learning (Tang et al. 2021), label propagation (Stikic et al. 2009) and co-training (Guan et al. 2007).”
What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks?
Qian, H., Tian, T., & Miao, C. (2022) · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3534678.3539134 · Cited by 67 · cited 1×
“1, most of these works have focused on contrastive approaches (Saeed et al. 2020; Khaertdinov et al. 2021; Qian et al. 2022; Wang et al. 2022; Jain et al. 2022; Zhang et al. 2022; Arrotta et al. 2023; Taghanaki et al. 2023; Meng et al. 2023).”
Exploring Contrastive Learning in Human Activity Recognition for Healthcare
Tang, C. I., Perez-Pozuelo, I., Spathis, D., & Mascolo, C. (2020) · arXiv · doi:10.48550/arxiv.2011.11542 · Cited by 67
Understanding Collapse in Non-contrastive Siamese Representation Learning
Li, A. C., Efros, A. A., & Pathak, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19821-2_28 · Cited by 61
MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series
Meng, Q., Qian, H., Liu, Y., Cui, L., Xu, Y., & Shen, Z. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i8.26098 · Cited by 52
Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables
Varamin, A. A., Abbasnejad, E., Shi, Q., Ranasinghe, D. C., & Rezatofighi, H. (2018) · Proceedings of the 15th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services · doi:10.1145/3286978.3287024 · Cited by 44 · cited 1×
“Other studies proposed generative meth-ods (Varamin et al. 2018; Haresamudram et al. 2020; Zhang et al. 2022) and demonstrated competitive performances.”
Taghanaki, S. R., Rainbow, M. J., & Etemad, A. (2023) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2023.3303438 · Cited by 31 · cited 1×
“1, most of these works have focused on contrastive approaches (Saeed et al. 2020; Khaertdinov et al. 2021; Qian et al. 2022; Wang et al. 2022; Jain et al. 2022; Zhang et al. 2022; Arrotta et al. 2023; Taghanaki et al. 2023; Meng et al. 2023).”
A unified generative model using generative adversarial network for activity recognition
Chan, M. H., & Noor, M. H. M. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02548-0 · Cited by 27 · cited 1×
“Another method of mitigating data scarcity is to generate synthetic data with generative models to enhance the limited available labeled data (Chan and Noor 2021).”
Investigating Enhancements to Contrastive Predictive Coding for Human Activity Recognition
Haresamudram, H., Essa, I., & Plötz, T. (2023) · 2023 IEEE International Conference on Pervasive Computing and Communications (PerCom) · doi:10.1109/percom56429.2023.10099197 · Cited by 27 · cited 2×
“…(JEPA) (Assran et al. 2023) and Mamba (Gu and Dao 2023), and new SSL approaches in the HAR domain such as Contrastive Predictive Coding (CPC) (Haresamudram et al. 2023), Spatial-Temporal Masked Autoencoder (STMAE) (Miao et al. 2024) and StatioCL (Wu et al. 2024) that may overcome the current…”
Investigating Enhancements to Contrastive Predictive Coding for Human Activity Recognition
Haresamudram, H., Essa, I., & Ploetz, T. (2022) · arXiv · Cited by 27 · cited 2×
“…(JEPA) (Assran et al. 2023) and Mamba (Gu and Dao 2023), and new SSL approaches in the HAR domain such as Contrastive Predictive Coding (CPC) (Haresamudram et al. 2023), Spatial-Temporal Masked Autoencoder (STMAE) (Miao et al. 2024) and StatioCL (Wu et al. 2024) that may overcome the current…”
XWARE—A customizable interoperability framework for pervasive computing systems
Roth, F. M., Becker, C., Vega, G., et al. (2018) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2018.03.005 · Cited by 25 · cited 1×
“These combined results are crucial for machine learning solutions on-device for all pervasive computing users (Roth et al. 2018).”
Self-citationCombining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity
Presotto, R., Ek, S., Civitarese, G., Portet, F., Lalanda, P., & Bettini, C. (2023) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp58114.2023.00022 · Cited by 24 · cited 3×
“4, aims to learn robust feature representations by predicting the latent representation of an input data sample from a partial view.”
InfluentialSelf-citationOn the Importance of Hyperparameters and Data Augmentation for Self-Supervised LearningPreprint
Wagner, D., Ferreira, F., Stoll, D., Schirrmeister, R., Müller, S., & Hutter, F. (2022) · arXiv.org · doi:10.48550/arxiv.2207.07875 · Cited by 24
StatioCL : Contrastive Learning for Time Series via Non-Stationary and Temporal Contrast
Wu, Y. Y., Dang, T., Spathis, D., Jia, H., & Mascolo, C. (2024) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3627673.3679732 · Cited by 11 · cited 3×
“…and Mamba (Gu and Dao 2023), and new SSL approaches in the HAR domain such as Contrastive Predictive Coding (CPC) (Haresamudram et al. 2023), Spatial-Temporal Masked Autoencoder (STMAE) (Miao et al. 2024) and StatioCL (Wu et al. 2024) that may overcome the current limitation raised in this study.”
Self-Supervised Time Series Representation Learning via Cross Reconstruction TransformerPreprint
Zhang, W., Yang, L. Q., Geng, S., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.09928 · Cited by 10
Capture-24: Activity tracker dataset for human activity recognition
Chan Chang, S., & Doherty, A. (2021) · University of Oxford · doi:10.5287/bodleian:nzvqj2ojw · Cited by 8 · cited 4×
“To the best of our knowledge, this is the first adaptation of MAE to the HAR domain that is closely aligned with the original implementation.”
InfluentialSelfAct: Personalized Activity Recognition Based on Self-Supervised and Active Learning
Arrotta, L., Civitarese, G., & Bettini, C. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-63989-0_19 · Cited by 6
Self-citation
Research works printed but not linked: 8
- Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: A public domain dataset for human activity recognition using smartphones. In: 21st European Symposium on Artificial Neural Networks, ESANN 2013, Bruges, Belgium, April 24–26, 2013 (2013)
- Baevski, A., Hsu, W.-N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: A general framework for self-supervised learning in speech, vision and language. In: Int. Conference on Machine Learning, pp. 1298–1312 (2022). PMLR
- Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607 (2020). PMLR
- Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2019). https://api.semanticscholar.org/CorpusID:52967399
- Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlus, D.: Hard negative mixing for contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 21798–21809 (2020)
- Miao, S., Chen, L., Hu, R.: Spatial-temporal masked autoencoder for multi-device wearable human activity recognition. Proc. ACM Interact. Mob. Wear. Ubiq. Technol. 7(4), 1–25 (2024)
- Qin, X., Chen, Y., Wang, J., Yu, C.: Cross-dataset activity recognition via adaptive spatial-temporal transfer learning. ACM IMWUT 3(4), 1–25 (2019)
- Zhang, X., Zhao, Z., Tsiligkaridis, T., Zitnik, M.: Self-supervised contrastive pre-training for time series via time-frequency consistency. Adv. Neural. Inf. Process. Syst. 35, 3988–4003 (2022)
Cited by
Khan, F. U., & Mian, A. N. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110753 · Cited by 5
Tanigaki, K., Maekawa, T., & Hara, T. (2026) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom67906.2026.11524533 · Cited by 3
Developing Switching Mechanism to Address Challenging Subjects in Sleep Stage Scoring
Kawabata, R., Horie, K., Lalanda, P., & Kitagawa, H. (2025) · IEEE International Conference on Healthcare Informatics (ICHI) · doi:10.1109/ichi64645.2025.00064 · Cited by 1
Self-citationAI in Wearable Imaging Devices
Adebayo, P. O., Aremu, I. B., & Babatunde, A. J. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-0903-3.ch006
Uncertainty-Driven Monitoring for ML-Based Autonomic Systems
Balditsyn, V., Lalanda, P., Vega, G., & Chollet, S. (2025) · IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS) · doi:10.1109/acsos66086.2025.00021 · Cited by 1
“3: Model architecture combining MAE with a HAR Transformer [28]. their self-attention mechanisms effectively capture temporal dependencies and long-range relationships.”
Self-citation
Metadata
- Authors
- Ek, S., Presotto, R., Civitarese, G., Portet, F., Lalanda, P., & Bettini, C.
- Affiliations
- Centre National de la Recherche Scientifique (FR)
- University of Milan (IT)
- Corresponding author
- Ek, Sannara
- Venue
- CCF Transactions on Pervasive Computing and Interaction
- Published
- 2025-03-30
- Volume
- 7
- Issue
- 3
- Pages
- 324-341
- ISSN
- 2524-521X (ISSN-L)
- 2524-5228
- OpenAlex
- W4409016795
- Cited by
- 15
- References
- 57
- Citations by year
- 2026: 6 · 2025: 8
- FWCI
- 4.26
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Licence
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- CCF Transactions on Pervasive Computing and Interaction (publishedVersion, public-domain)
- SSRN Electronic Journal (acceptedVersion)
- arXiv (Cornell University) (submittedVersion, public-domain)
- HAL (submittedVersion, cc-by)
- Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano) (submittedVersion, other-oa)
- arXiv (Cornell University)
- Funders
- Naval Group
- Nextgeneration
- 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
- Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Physical Activity and Health
- Keywords
- human activity recognition, wearable sensors, self-supervised learning, contrastive learning, generative models, prediction model, masked autoencoder, SimCLR, limited labeled data, pre-trained models
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-11, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
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
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.