The DOI matches its Crossref record, with a small difference in title or year; the references it cites are not checked yet.
Learning from the Best: Contrastive Representations Learning Across Sensor Locations for Wearable Activity Recognition
Open accessAbstract
We address the well-known wearable activity recognition problem of having to work with sensors that are non-optimal in terms of information they provide but have to be used due to wearability/usability concerns (e.g. the need to work with wrist-worn IMUs because they are embedded in most smart watches). To mitigate this problem we propose a method that facilitates the use of information from sensors that are only present during the training process and are unavailable during the later use of the system. The method transfers information from the source sensors to the latent representation of the target sensor data through contrastive loss that is combined with the classification loss during joint training (fig. 1). We evaluate the method on the well-known PAMAP2 and Opportunity benchmarks for different combinations of source and target sensors showing average (over all activities) F1 score improvements of between 5% and 13% with the improvement on individual activities, particularly well suited to benefit from the additional information going up to between 20% and 40%.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Learning from the Best (LftB) adopts a flexible approach to cross-device contrastive learning by using individual encoder and translator networks for each sensor location to separate the embedding spaces among devices.
“Also leveraging time-synchronized sensor time series, 'Learning from the Best' (LftB) [55] adopts a flexible approach to cross-device contrastive learning by using individual encoder and translator networks for each sensor location to separate the embedding spaces among devices.”
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 [55]
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
The citation lists haven’t been fetched yet
References 11 · Cited by 12
Research works printed but not linked: 12
- 10.1109/CVPR.2017.502 · DOI · Paper page
- Pranay Gupta , Anirudh Thatipelli , Aditya Aggarwal , Shubh Maheshwari , Neel Trivedi , Sourav Das , and Ravi Kiran Sarvadevabhatla . 2021. Quo vadis, skeleton action recognition?International Journal of Computer Vision 129, 7 ( 2021 ), 2097–2112. Pranay Gupta, Anirudh Thatipelli, Aditya Aggarwal, Shubh Maheshwari, Neel Trivedi, Sourav Das, and Ravi Kiran Sarvadevabhatla. 2021. Quo vadis, skeleton action recognition?International Journal of Computer Vision 129, 7 (2021), 2097–2112.
- 10.1145/3460421.3480421 · DOI
- Saif Mahmud , M Tanjid Hasan Tonmoy , Kishor Kumar Bhaumik , AKM Mahbubur Rahman , M Ashraful Amin , Mohammad Shoyaib , Muhammad Asif Hossain Khan , and Amin Ahsan Ali . 2020 . Human Activity Recognition from Wearable Sensor Data Using Self-Attention . In ECAI 2020. IOS Press, 1332–1339. Saif Mahmud, M Tanjid Hasan Tonmoy, Kishor Kumar Bhaumik, AKM Mahbubur Rahman, M Ashraful Amin, Mohammad Shoyaib, Muhammad Asif Hossain Khan, and Amin Ahsan Ali. 2020. Human Activity Recognition from Wearable Sensor Data Using Self-Attention. In ECAI 2020. IOS Press, 1332–1339.
- Pedro Morgado , Yi Li , and Nuno Nvasconcelos . 2020 . Learning representations from audio-visual spatial alignment . Advances in Neural Information Processing Systems 33 (2020), 4733 – 4744 . Pedro Morgado, Yi Li, and Nuno Nvasconcelos. 2020. Learning representations from audio-visual spatial alignment. Advances in Neural Information Processing Systems 33 (2020), 4733–4744.
- 10.1109/CVPR46437.2021.01229 · DOI
- 10.1016/j.cviu.2021.103219 · DOI · Paper page
- Sungho Suh , Vitor Fortes Rey , and Paul Lukowicz . 2022 . Adversarial Deep Feature Extraction Network for User Independent Human Activity Recognition. In 2022 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE, 217–226 . Sungho Suh, Vitor Fortes Rey, and Paul Lukowicz. 2022. Adversarial Deep Feature Extraction Network for User Independent Human Activity Recognition. In 2022 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE, 217–226.
- Aaron Van den Oord , Yazhe Li , and Oriol Vinyals . 2018. Representation learning with contrastive predictive coding. arXiv e-prints ( 2018 ), arXiv–1807. Aaron Van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv e-prints (2018), arXiv–1807.
- Huiyuan Yang Han Yu Kusha Sridhar Thomas Vaessen Inez Myin-Germeys and Akane Sano. 2022. More to Less (M2L): Enhanced Health Recognition in the Wild with Reduced Modality of Wearable Sensors. arXiv preprint arXiv:2202.08267(2022). Huiyuan Yang Han Yu Kusha Sridhar Thomas Vaessen Inez Myin-Germeys and Akane Sano. 2022. More to Less (M2L): Enhanced Health Recognition in the Wild with Reduced Modality of Wearable Sensors. arXiv preprint arXiv:2202.08267(2022). · DOI
- Jianbo Yang Minh Nhut Nguyen Phyo Phyo San Xiao Li Li and Shonali Krishnaswamy. 2015. Deep convolutional neural networks on multichannel time series for human activity recognition. In Twenty-fourth international joint conference on artificial intelligence. Jianbo Yang Minh Nhut Nguyen Phyo Phyo San Xiao Li Li and Shonali Krishnaswamy. 2015. Deep convolutional neural networks on multichannel time series for human activity recognition. In Twenty-fourth international joint conference on artificial intelligence.
- 10.1145/3550320 · DOI
Metadata
- Authors
- Fortes Rey, V., Suh, S., & Lukowicz, P.
- Affiliations
- Embedded Intelligence, Deutsches Forschungszentrum für Künstliche Intelligenz, Germany and Informatik, University of Kaiserslautern, Germany
- University of Kaiserslautern (DE)
- Venue
- Proceedings of the 2022 ACM International Symposium on Wearable Computers
- Publisher
- ACM
- Published
- 2022-09-11
- Pages
- 28-32
- OpenAlex
- W4313144102
- Cited by
- 12
- References
- 11
- Citations by year
- 2025: 5 · 2024: 3 · 2023: 3
- FWCI
- 1.00
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM International Symposium on Wearable Computers (ISWC) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Carl Zeiss Stiftung (P2021-02-009)
- BMBF (German Federal Ministry of Education and Research) (01IW21003)
- 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
- wearable activity recognition, sensor fusion, contrastive learning, inertial measurement unit, wrist-worn sensors, smartwatches, latent representations, PAMAP2, Opportunity dataset
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
