Multi-task Self-Supervised Learning for Human Activity Detection
Open accessThe DOI matches its Crossref record; 85 of the 85 references it cites were found in a registry or an index.
Abstract
Deep learning methods are successfully used in applications pertaining to ubiquitous computing, pervasive intelligence, health, and well-being. Specifically, the area of human activity recognition (HAR) is primarily transformed by the convolutional and recurrent neural networks, thanks to their ability to learn semantic representations directly from raw input. However, in order to extract generalizable features massive amounts of well-curated data are required, which is a notoriously challenging task; hindered by privacy issues and annotation costs. Therefore, unsupervised representation learning (i.e., learning without manually labeling the instances) is of prime importance to leverage the vast amount of unlabeled data produced by smart devices. In this work, we propose a novel self-supervised technique for feature learning from sensory data that does not require access to any form of semantic labels, i.e., activity classes. We learn a multi-task temporal convolutional network to recognize transformations applied on an input signal. By exploiting these transformations, we demonstrate that simple auxiliary tasks of the binary classification result in a strong supervisory signal for extracting useful features for the down-stream task. We extensively evaluate the proposed approach on several publicly available datasets for smartphone-based HAR in unsupervised, semi-supervised and transfer learning settings. Our method achieves performance levels superior to or comparable with fully-supervised networks trained directly with activity labels, and it performs significantly better than unsupervised learning through autoencoders. Notably, for the semi-supervised case, the self-supervised features substantially boost the detection rate by attaining a kappa score between 0.7 - 0.8 with only 10 labeled examples per class. We get similar impressive performance even if the features are transferred from a different data source. Self-supervision drastically reduces the requirement of labeled activity data, effectively narrowing the gap between supervised and unsupervised techniques for learning meaningful representations. While this paper focuses on HAR as the application domain, the proposed approach is general and could be applied to a wide variety of problems in other areas.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source doesn’t support the claim as written.
In the citing paper
“In contrast, previous studies applied self-supervised training and fine-tuning only on the same data sources24,27,40, making it necessary to pre-train on every new dataset in practical applications.”
From Self-supervised learning for human activity recognition using 700,000 person-days of wearable data (2024) · cites this paper as [27]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For windows of sensor data, Saeed et al. [166] apply each transformation with a probability of 50%, and passed the probabilistically transformed windows through a common convolutional encoder.”
From Past, Present, and Future of Sensor-based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task (2025) · cites this paper as Saeed et al. [166]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Haresamudram et al. [81] show that the SimCLR framework [184] and multi-task self-supervised learning [166], outperform other approaches, including BYOL, SimSiam, masked reconstruction, CPC and autoencoders for HAR.”
From Past, Present, and Future of Sensor-based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task (2025) · cites this paper as [166]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The established multi-task self-sup. Ref. [15] framework is ill-suited for discrete representation learning, with significant reductions in performance throughout, consistently performing worse by approx. 10% for most datasets and peaking at around 29% for Mobiact.”
From Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition (2024) · cites this paper as [15]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“We show that our method outperforms existing self-supervised methods in HAR for UCI HAR, MotionSense, and HAPT datasets.”
From Self-supervised Human Activity Recognition by Learning to Predict Cross-Dimensional Motion (2021) · cites this paper as [19]
Experimental — accuracy not yet measured
19 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“These techniques have achieved indisputable empirical success across a broad spectrum of problems [4, 21, 28, 36, 43, 56, 65, 66] thanks to the increasing dataset sizes and computing power availability.”
BackgroundAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 3×
“We use ReLU as non-linearity in all the layers (except the output) and train a network with Adam optimizer [26] for a maximum of 30 epochs with a learning rate of 0.”
MethodInfluentialLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
(2008) · Journal of Machine Learning Research · Cited by 33,051
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 1×
“owledge transfer se−ings (such as features, instances, weights) from existing labeled data of some related task or domain. For a detailed review of transfer learning, we refer an interested reader to [53]. 2.4 Semi-supervised Learning Semi-supervised learning provides a compelling framework for leveraging unlabeled da…”
BackgroundInfluentialSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“These techniques have achieved indisputable empirical success across a broad spectrum of problems [4, 21, 28, 36, 43, 56, 65, 66] thanks to the increasing dataset sizes and computing power availability.”
Background(2010) · International Conference on Machine Learning · Cited by 13,995
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 3×
“is inherent limitation of the fully-supervised learning paradigm emphasizes the importance of unsupervised learning to leverage a large amount of unlabeled data for representation learning [8] that can be easily acquired in a real-world seing.”
BackgroundInfluentialCaruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636 · cited 2×
“e goal of multi-task learning (MTL) is to enhance the learning eciency and accuracy through simultaneously optimizing multiple objectives based on shared representations and exploiting relations among the tasks [10].”
BackgroundDeepFace: Closing the Gap to Human-Level Performance in Face Verification
Taigman, Y., Yang, M., Ranzato, M., & Wolf, L. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.220 · Cited by 6,542 · cited 1×
“ese techniques have achieved indisputable empirical success across a broad spectrum of problems [4, 21, 28, 35, 43, 56, 65, 66] thanks to the increasing dataset sizes and computing power availability.”
Background
Research works printed but not linked: 7
- Baldi Pierre, 2012, Proceedings of ICML workshop on unsupervised and transfer learning. 37--49
- Chatzaki Charikleia, 2016, International Conference on Information and Communication Technologies for Ageing Well and e-Health. Springer, 100--118
- 10.5555/3104322.3104425 · doi:10.5555/3104322.3104425
- 10.5555/3305890.3305968 · doi:10.5555/3305890.3305968
- Plötz Thomas, 2011, IJCAI Proceedings-International Joint Conference on Artificial Intelligence, 22
- Razavian Narges, 2016, Machine Learning for Healthcare Conference. 73--100
- Wawrzyniak S., 2015 Federated Conference on Computer Science and Information Systems (FedCSIS). 411--416
Cited by
Items 301–345 of 345
Deep unsupervised methods towards behavior analysis in ubiquitous sensor data
Sharma, M., Tiwari, S., Ruhela, G., Chakraborty, S., & Banerjee, D. S. (2021) · Internet of Things · doi:10.1016/j.iot.2021.100486
Contrastive Self-Supervised Learning for Stress Detection from ECG Data
Rabbani, S., & Khan, N. (2023) · doi:10.32920/22734386
ViFiT: Reconstructing Vision Trajectories from IMU and Wi-Fi Fine Time Measurements
Cao, B. B., Alali, A., Liu, H., Meegan, N., Gruteser, M., Dana, K., Ashok, A., & Jain, S. (2023) · ACM MobiCom Workshop on Integrated Sensing and Communications Systems (ISACom) · doi:10.1145/3615984.3616503 · Cited by 2
“Recent development in phone data processing, especially IMU, has utilized deep learning models in various applications such as human activity recognition (HAR) [5, 6, 7, 8] , pedestrian multimodal association [1, 2, 3] and etc.”
BackgroundApplication of Pre Training New Paradigm in Time Series
Huang, J., Zhang, X., Shen, S., Jiang, Z., & Niu, Y. (2023) · International Conference on Information Science, Parallel and Distributed Systems (ISPDS) · doi:10.1109/ispds58840.2023.10235694
Noise-Aware Self-Supervised Denoising for Electrocardiogram Anomaly DetectionPreprint
Chen, P., Deng, M., Zhang, D., Zhou, B., & Fan, H. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4601063
Hsu, J.-H., Tseng, H.-W., Wu, C., Lin, E. C., & Chen, P. S. (2023) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc58517.2023.10317215
“To address this limitation, this study proposes the incorporation of multitask self-supervised learning [13], which allows the detection model to gain a more comprehensive understanding of the data by considering both temporal and data type correlations.”
MethodActive contrastive coding reducing label effort for sensor-based human activity recognition
Li, Z., Liu, H., Huan, Z., & Liang, J. (2023) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-234804
“Four backbones of CPC [23], TPN [20], DeepConvL-STM [24] and the Conv+Self-Attention proposed by us are compared.”
Contrastive Learning Based Human Activity Recognition Using Body Sensors
Xie, C., Zhou, Y., Yu, D., Sun, S., & Zhang, X. (2023) · International Conference on Big Data Computing and Communications (BigCom) · doi:10.1109/bigcom61073.2023.00043 · Cited by 1
“Saeed et al. [25] proposed a new self-supervised technique capable of learning features of activity from sensory data without activity labels, while learning a multi-task temporal convolutional network to identify transformations applied to that input signal, extracting useful features for…”
BackgroundA review on devices and learning techniques in domestic intelligent environment
Ye, J., Wang, M., Zhong, J., & Jiang, H. (2024) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-024-04759-1
Smith, D., Baumgartner, P., McGinness, L. P., Kapoor, R., Rana, M., Rahman, A., Schutt, A., & Tartaglia, E. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4792141
Dheeravath, K., & Saritha, S. J. (2024) · International Journal of Computing and Digital Systems · doi:10.12785/ijcds/160126
“On the other hand, several unsupervised approaches are proposed ([26]; [27]; [28]), all based on self-supervised objectives and requiring no labeled data.”
Feature representation learning for human activity recognition
Khaertdinov, B. (2024) · Research Publications (Maastricht University) · doi:10.26481/dis.20240618bk · Cited by 1
Exploring Community from Electricity with Human Community InteractionPreprint
Fu, Z., Yang, Y., Chen, Y., & Ma, L. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4877288
Haresamudram, H., Essa, I. A., & Plötz, T. (2024) · International Conference on Activity and Behavior Computing (ABC) · doi:10.1109/abc61795.2024.10651688 · Cited by 1
“Going beyond hand-crafting of features [18], [19], recent approaches learn useful representations from data itself, through supervised and unsupervised/self-supervised learning [1], [20].”
BackgroundMethodInfluentialAssessing Bias in Self-supervised and Supervised Models for Temporal Data
Liatsikou, M., Yfantidou, S., & Vakali, A. I. (2024) · Hellenic Conference on Artificial Intelligence · doi:10.1145/3688671.3688753 · Cited by 1
“The baseline supervised model (1D CONV), inspired by the work of Saeed et al. [31], comprises 3 1D convolutional layers and 2 fully-connected layers.”
Fast Adapting Few-Shot Federated Learning System for Human Activity Recognition
Zhang, Z., & Zhao, Y. (2024) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa63168.2024.00264 · Cited by 2
“2) Dense Sampling: Most of the previous work [19], [20] uses a low overlap rate(less than 50 percent), to divide the IMU data, but this can lead to underutilization of the data.”
SSCMIRG: Self-Supervised Contrastive Learning for Medical Images with Report Generation
Kumar, R., & Arulkumar, N. (2024) · Mapana Journal of Sciences · doi:10.12723/mjs.sp3.6
Vu, Q. N. P., Lago, P., Bader, S., & Inoue, S. (2025) · International Conference on Activity and Behavior Computing (ABC) · doi:10.1109/abc64332.2025.11118576
“Learned representations have been proven to be more effective compared to hand-crafted features in terms of providing more robust results with small variations in the input features [15], [17], [18], [20], [53], [54].”
Inertial Signal Forecasting With Foundation Model Techniques
Wieland, C., & Pankratius, V. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3603456 · Cited by 3
“Transformation detection approaches apply random augmentations to input signals and learn to recognize the applied transformations in a multitask learning environment [38].”
Indoor Localization from Large-Scale Poor-Quality Crowdsourcing Wifi Data for On-Demand Delivery
Guo, K., Zheng, S., Zhou, H., Zhang, Y., Yan, K., Shen, G., Du, H., & Li, X. (2025) · International Workshop on Quality of Service · doi:10.1109/iwqos65803.2025.11143426
Building Generalizable Deep Learning Solutions for AIoT Applications
Xu, H. (2025) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3711875.3736673
“A primary challenge in existing deep learning approaches [6, 11, 12, 15, 31] is their reliance on supervised learning, necessitating extensive labeled sensor data for constructing general sensing models.”
InfluentialUnsupervised, Semi-Supervised, and Self-Supervised Learning for Climate Applications
Kumar, G., Sankar, M., Arunarani, A. R., Sandeep, C. S., Kumar, S., Kunwar, F. B., & Bhoopathy, V. (2025) · Advances in geospatial technologies book series · doi:10.4018/979-8-3373-3501-8.ch008
Dual-Space Masked Reconstruction for Robust Self-Supervised Human Activity Recognition
Xiao, S., Deng, J., Tang, C., & Huang, Z. (2025) · Proceedings of the 34th ACM International Conference on Information and Knowledge Management · doi:10.1145/3746252.3761215
“First, collecting sensor signals from user devices and annotating them with labels may compromise the scalability of data collection [28], as manual annotation of raw sensor data constitutes a labor-intensive task requiring substantial temporal and financial resources.”
Bhattacharjee, S. D., Chhabria, J., & Pallapothula, V. K. N. (2025) · IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies · doi:10.1145/3721201.3724415
“Valence-3 SSL [35] 78.99 76.66 SimpDCNN [24] 59.2 51.95 SigRep [8] 64.83 60.25 MULT [32] 63.14 62.5 CorrNet [36] 65.14 53.00 S&T[25] 70 [24] 56.8 53.85 SigRep [8] 65.07 61.08 MULT [32] 62.15 58.48 CorrNet [36] 58.22 55.00 S&T[25] 68.36 58.22 ActDiffNet (ours) 85.64 84.37”
InfluentialNI-MTSC: Neighborhood Interpolation Data Augmentation-based Multivariate Time Series Classification
Yang, C., Fan, Z., Gou, J., & Wang, C. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229225
“Most time series data augmentation methods tend to draw on relevant technical means from the fields of image and language [27]–[29].”
Experience Paper: Adopting Activity Recognition in On-demand Food Delivery Business
Xu, H., Zhang, Y., Gao, W., Shen, G., & Li, M. (2025) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3680207.3765261 · Cited by 5
“Among these applications, Human Activity Recognition (HAR) has emerged as a pivotal technology that garnered significant attention in research [16, 23, 36, 46, 47, 50].”
InfluentialYang, L., Zhou, M., Wang, X., Yang, Y., Yang, P., & Qi, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5530660
LiDArgus: Accommodating Diverse Privacy Preferences in LiDAR Sensing Through Configurable Sub-Zoning
Li, B., Yang, J., Jain, A., Newberry, W., & Yang, X.-D. (2025) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3746059.3747724
“Much prior work has focused on vision-based methods, using cameras to identify activities [27, 49, 61, 65].”
Zhu, Y., Huang, S., & Shi, Y. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3786597
“In computer vision, various techniques are used to augment image data, such as cropping, rotating, flipping, and scaling, which have consistently demonstrated success in improving model generalization and robustness.”
Yeke, M. C., Gelen, S. S., Fil, H., Yalcin, M. M., Gümüş, A., Yazgan, İ., & Demirkol, D. O. (2026) · Biosensors and Bioelectronics X · doi:10.1016/j.biosx.2025.100733 · Cited by 2
Self-Supervised Anomaly Detection for Parkinson’s Disease in Free-Living Environment
Huang, C., Wang, X., Peng, X., Yue, P., Qi, J., Yang, Y., & Yang, P. (2025) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin64977.2025.11279622
“We apply six transformations inspired by [16], including noise addition, reverse, permutation, scaling, negation, and smoothing.”
Chhabria, J., Verma, R., Bhattacharjee, S. D., Xu, W., & Bo, W. (2025) · Wearable and Implantable Body Sensor Networks · doi:10.1109/bsn66969.2025.11337342
“…[13] 75.21 64.12 SimpDCNN [16] 78.3 74.59 RF [13] 76.17 66.33 LDA [13] 68.85 58.18 SigRep [14] 78.13 77.35 SSL [3] 78.7 75.98 S&T [17] 69 [16] 59.2 51.95 SigRep [14] 64.83 60.25 MULT [18] 63.14 62.5 CorrNet [19] 65.14 53.00 S&T [17] 70 [16] 56.8 53.85 SigRep [14] 65.07 61.08 MULT [18]…”
InfluentialEnd-to-end non-invasive ECG signal generation from PPG signal: a self-supervised learning approach
Yalcin, M., & Latoschik, M. E. (2026) · Frontiers in Physiology · doi:10.3389/fphys.2026.1694995 · Cited by 2
Human Activity Recognition Reimagined: The CGRNHAR Self-Supervised Approach
Challa, A. K. R., Raavi, V. K., Bandari, H., Gude, D. K., & Kumar, S. (2025) · Global AI Summit - International Conference on Artificial Intelligence and Emerging Technology (AI Summit) · doi:10.1109/aisummit66170.2025.11411187
“According to [22] the research selects twenty percent of cases randomly for testing purposes and sets twenty percent of remaining subjects into validation groups.”
Advancing Emotion Recognition Through Physiological Signal Fusion and Machine Learning
Tarawneh, A., Kamel, A., Khouadja, O., & Naceur, M. S. (2025) · International Conference on Cyberworlds (CW) · doi:10.1109/cw68232.2025.00057
“We aim to build models using both single and hybrid physiological signals (ECG, TEB, EDA) for the most accurate results [6].”
MicroAI : embedded artificial intelligence for human activity recognition on smart glasses
Novac, P.-E. (2022) · theses.fr (ABES) · doi:10.70675/77c14a3ez0f87z4c4dza876z9064b1b107ec · Cited by 3
Characterization of radioactivity signals by embedded machine learning
Hachem, A. (2024) · theses.fr (ABES) · doi:10.70675/f51ce3dbz0047z462az9f44z482383015d52 · Cited by 2
Efficient federated self-supervised human activity recognition via delta-loss client clustering
Bukit, T. A., Yahya, B. N., & Lee, S. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106251
da Silva, T. B. C., Santiago, H. D. C., & Fernandes, B. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11619-1 · Cited by 1
Recognition of eating episodes via commercial smartwatch sensors analysis
Vedovelli, L., Bhuyan, M. J., Lanera, C., Baldi, I., Berchialla, P., Gregori, D., & NOTION Working Group (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001539
“Semi-supervised and self-supervised learning approaches may help leverage the abundance of unlabeled wearable data [52].”
Jaiswal, P., Kaushik, A., Lawless, F., Malaquias, T. D. M., & McCaffery, F. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-30809-2_19
GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery
Hong, Z., Li, Z., Fan, X., Yang, G., Guo, B., Wang, H., He, T., & Zhang, D. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770854.3783921 · Cited by 2
“Following previous studies [7, 50, 55, 75, 76, 80], we utilize UCI [54], Shoaib [60], Motion [45], and HHAR [63] datasets.”
Shuhui, G., Cao, M., & Wan, J. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01212-8
BADUR, Y., & Serin, F. (2026) · Applied Sciences · doi:10.3390/app162010185
Metadata
- Authors
- Saeed, A., Ozcelebi, T., & Lukkien, J.
- Affiliations
- Eindhoven University of Technology (NL)
- Eindhoven University of Technology, Eindhoven, The Netherlands
- ORCID
- Saeed, Aaqib
- Venue
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Published
- 2019-06-21
- Volume
- 3
- Issue
- 2
- Pages
- 1-30
- ISSN
- 2474-9567 (ISSN-L)
- OpenAlex
- W3099025572
- Cited by
- 346
- References
- 85
- Citations by year
- 2026: 20 · 2025: 65 · 2024: 82 · 2023: 71 · 2022: 49 · 2021: 42 · 2020: 17
- FWCI
- 11.94
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (publishedVersion, public-domain)
- TU/e Research Portal (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- TU/e Research Portal (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- Horizon 2020 Framework Programme (737422)
- 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, self-supervised learning, unsupervised feature learning, multi-task learning, temporal convolutional network, smartphone sensing, semi-supervised learning, transfer learning, unlabeled 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
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.