Investigating Enhancements to Contrastive Predictive Coding for Human Activity Recognition
Open accessThe DOI matches its Crossref record; 65 of the 65 references it cites were found in a registry or an index; 14 of the 14 sources its claims cite were checked for support.
Abstract
The dichotomy between the challenging nature of obtaining annotations for activities, and the more straightforward nature of data collection from wearables, has resulted in significant interest in the development of techniques that utilize large quantities of unlabeled data for learning representations. Contrastive Predictive Coding (CPC) is one such method, learning effective representations by leveraging properties of time-series data to setup a contrastive future timestep prediction task. In this work, we propose enhancements to CPC, by systematically investigating the encoder architecture, the aggregator network, and the future timestep prediction, resulting in a fully con-volutional architecture. Across sensor positions and activities, our method shows substantial improvements on four of six target datasets, demonstrating its ability to empower a wide range of application scenarios. Further, in the presence of very limited labeled data, our technique significantly outperforms both supervised and self-supervised baselines, positively impacting situations where collecting only a few seconds of labeled data may be possible. This is promising, as CPC does not require specialized data transformations or reconstructions for learning effective representations.
Overview
CoChat Summary
TL;DR
The paper systematically enhances Contrastive Predictive Coding (CPC) for wearable human activity recognition by replacing the encoder with strided convolutions, replacing the GRU aggregator with causal convolutions, and performing future-timestep prediction at each timestep. The enhanced CPC improves over prior CPC and other self-supervised baselines on four of six target datasets, especially for locomotion-style activities and limited labeled data.
Key findings
- Enhanced CPC + MLP achieved test F1-scores of 59.25 ± 1.31 (HHAR), 40.87 ± 0.50 (Myogym), 78.07 ± 0.27 (Mobiact), 89.35 ± 0.32 (Motionsense), 53.79 ± 0.83 (MHEALTH), and 58.19 ± 1.22 (PAMAP2), compared with CPC at 55.59 ± 1.40, 41.03 ± 0.52, 73.44 ± 0.36, 84.08 ± 0.59, 41.03 ± 0.52, and 55.22 ± 0.92, respectively.
- The paper reports substantial improvements on four of six target datasets (HHAR, Mobiact, Motionsense, MHEALTH); PAMAP2 is similar and Myogym is worse than CPC.
- Replacing the GRU aggregator with causal convolutions improved HHAR and leg-based datasets, with MHEALTH improving by around 9% and PAMAP2 by around 6%; the new future-prediction task improved four benchmark datasets.
- With limited labeled data, enhanced CPC generally outperformed other self-supervised methods; for HHAR it was generally best when at least 25 annotated windows were available, and for Mobiact it significantly improved over the Conv. classifier.
Methods
- Pre-training used the Capture-24 wrist accelerometer dataset (100 Hz, downsampled to 50 Hz, around 2,500 hours, 10% of windows), split by users 90:10 into train/validation; evaluation used six target datasets: HHAR and Myogym (wrist), Mobiact and Motionsense (waist), MHEALTH and PAMAP2 (leg/ankle).
- Enhanced CPC uses a four-layer 1D convolutional encoder with (32, 64, 128, 256) filters, kernel size (4, 1, 1, 1), stride (2, 1, 1, 1), reflect padding, ReLU, and dropout p = 0.2; a causal convolutional aggregator tuned over (2, 4, 6) blocks with kernel sizes (2, 3, 4, 5, 6, 7), 256 filters, group normalization, ReLU, and skip connections; and future-timestep prediction at each timestep using InfoNCE with negatives from the entire batch.
- Experiments used 2-second windows, 50% overlap for target datasets, five-fold cross-validation, random search for hyperparameters, 50 training epochs, Adam optimizer, and batch size 256; baselines included Multi-task self-supervision, Autoencoder, SimCLR, CPC, Conv. classifier, DeepConvLSTM, and GRU classifier.
Limitations
- The paper states that predicting future timesteps at each sample is computationally expensive, though this is somewhat mitigated by the strided encoder; it also notes that CPC and enhanced CPC perform poorly on fine-grained activities such as Myogym compared with SimCLR and Autoencoder.
- The paper states that increased striding reduces temporal resolution and negatively impacts downstream recognition, and that enhanced CPC can likely be improved with more pre-training data and deeper encoder/aggregator networks.
- Evident from the text: pre-training uses only wrist accelerometer data from Capture-24, evaluation is limited to accelerometer-based datasets, and hyperparameter search is limited to 20 pre-training combinations and 50 fine-tuning combinations.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
10 Valid · 4 Not valid · 1 Not checked · 70 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“as matching the frequency is more effective [27].”
What the sources say
- Supportedcites [27] source
Section 5.1.3, “Variations in the Sampling Rate,” concludes that matching source and target sampling rates is preferable because different rates reduce activity-recognition performance. The claim accurately paraphrases that finding in the paper’s self-supervised wearable activity-recognition setting. (LLM, conf=0.94)
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.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“as [27] showed that the performance is comparable to using the entire train dataset”
What the sources say
- Supportedcites [27] source
In “Effect of the number of training windows on activity recognition” (page not provided), the paper says that, as a general trend, self-supervised methods achieve comparable or better performance using only 10% of the training windows. It describes randomly sampling those windows for pre-training and comparing results across sample sizes up to 100%. (LLM, conf=0.94)
boosted- 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.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“as utilizing self-supervised models from the wrist → waist is typically not as effective as wrist → wrist (where the location is common) or wrist → leg (where activities can have tandem movements between the hands and the legs) [27].”
What the sources say
- Supportedcites [27] source
Section 5.2.3 says self-supervision is more effective when transferring to wrist-based datasets or to the leg, and links the leg result to synchronized wrist-and-leg motion. Section 5.1.1 reports an overall trend of worse or similar performance for wrist-to-waist transfer, versus comparable performance or gains for wrist-to-leg transfer. The supplied passages do not give page numbers. (LLM, conf=0.93)
hedgedstates an association- 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.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“as it is beneficial for performance [27].”
What the sources say
- Supportedcites [27] source
Section 4.4 (Data Preparation) says the means and variances from the Capture-24 training set were applied to the target datasets. Section 6.1 reports that using those statistics improved activity-recognition performance compared with normalizing from the target data itself. (LLM, conf=0.91)
plainstates a cause- 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.
- Supported
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
“Through our experiments, we observe the superior performance of our enhanced CPC over the previous version of CPC, demonstrating the effectiveness of our approach for practical HAR applications.”
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.
46 more claims
Create a free account to see all 85 claims and every source verdict.
- It may state two separate claims as one. 25
- Probably not a substantial claim. 9
- The quote only partly states this claim. 1
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, if no annotated data are available for the unseen activities, cross-modal contrastive training (e.g., between sensor data and videos/text descriptions) is a good option [61,82,135,201].”
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 [82]
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 majority of these works have focused on contrastive approaches [23, 24, 25, 26, 27].”
From Comparing self-supervised learning techniques for wearable human activity recognition (2025) · cites this paper as [23]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Furthermore, investigations into enhancements of CPC for HAR, as presented by subsequent research [79,82], have yielded fully convolutional architectures that exhibit substantial improvements across diverse datasets and activity types.”
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 [82]
The cited source says what the claim attributes to it.
In the citing paper
“prior works such as [16,30] have utilized it as the base for self-supervised pre-training, allowing us to compare our results against those works.”
From Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition (2024) · cites this paper as [30]
In the citing paper
“The resulting ‘Enhanced CPC’ demonstrates substantial improvements over the original framework [68] as well as outperforms state-of-the-art self-supervision on four of six target datasets.”
From Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition (2024) · cites this paper as [30]
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
§ C. Investigating the Components of the CPC Framework
“replacing the encoder from CPC to the network from enhanced CPC results in a general reduction in performance across all target datasets except MHEALTH, where the performance slightly improves.”
§ B. Performance on Limited Amounts of Labeled Data
“| CPC | 55.59 ± 1.40 | 41.03 ± 0.52 | 73.44 ± 0.36 | 84.08 ± 0.59 | 41.03 ± 0.52 | 55.22 ± 0.92 | | CPC + new encoder | 51.21 ± 0.93 | 39.68 ± 0.78 | 71.43 ± 0.54 | 84.42 ± 0.45 | 42.06 ± 0.92 | 53.53 ± 0.96 |”
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
§ A. Activity Recognition Performance
“The utilization of the MLP classifier uniformly boosts the performance of enhanced CPC relative to the previous version, by around 4% on most datasets, and over 10% on MHEALTH.”
§ B. Performance on Limited Amounts of Labeled Data
“| CPC | 55.59 ± 1.40 | 41.03 ± 0.52 | 73.44 ± 0.36 | 84.08 ± 0.59 | 41.03 ± 0.52 | 55.22 ± 0.92 |”
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“Reconstructing randomly masked out portions of the input was studied for representation learning in [20], where a Transformer [31] encoder was utilized.”
MethodAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“The Adam optimizer [46] is utilized (unless otherwise specified), with a batch size of 256.”
MethodLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071
(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
Efficient Estimation of Word Representations in Vector Space
Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1301.3781 · Cited by 26,568 · cited 1×
“This training paradigm of ‘pretrain-then-finetune’ has resulted in significant performance improvements across domains such as computer vision [11], speech processing [12]–[15], natural language processing [16]–[18], and human activity recognition from wearables [19]–[21].”
Background(2010) · International Conference on Machine Learning · Cited by 13,995
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
(2012) · Cited by 8,009
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
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×
“SimSiam [27], [33] and Bootstrap Your Own Latent (BYOL)”
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 3×
“The supervised baselines comprise DeepConvLSTM [51], an established network for recognizing activities, a Conv.”
BackgroundUnsupervised Representation Learning by Predicting Image Rotations
Gidaris, S., Singh, P., & Komodakis, N. (2018) · arXiv · doi:10.48550/arxiv.1803.07728 · Cited by 2,477
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
wav2vec: Unsupervised Pre-Training for Speech Recognition
Schneider, S., Baevski, A., Collobert, R., & Auli, M. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-1873 · Cited by 1,290
Um, T. T., Pfister, F. M. J., Pichler, D., Endo, S., Lang, M., Hirche, S., Fietzek, U., & Kulić, D. (2017) · Proceedings of the 19th ACM International Conference on Multimodal Interaction · doi:10.1145/3136755.3136817 · Cited by 729 · cited 1×
“Another contrastive learning method includes SimCLR [24], [26], [27], which heavily relies on data transformations [32] as it contrasts two randomly augmented views of the data in a siamese setup, resulting in highly effective representations.”
MethodStisen, 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
Wearable Assistant for Parkinson’s Disease Patients With the Freezing of Gait Symptom
Bachlin, M., Plotnik, M., Roggen, D., Maidan, I., Hausdorff, J. M., Giladi, N., & Troster, G. (2010) · IEEE Transactions on Information Technology in Biomedicine · doi:10.1109/titb.2009.2036165 · Cited by 693 · cited 1×
“formed, has a multitude of applications, including health [1]– [3], industry [4]–[6], and fitness tracking [7], [8].”
BackgroundUm, T. T. (n.d.) · mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) · Cited by 602
mHealthDroid: A Novel Framework for Agile Development of Mobile Health Applications
Banos, O., Garcia, R., Holgado-Terriza, J. A., Damas, M., Pomares, H., Rojas, I., Saez, A., & Villalonga, C. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-13105-4_14 · Cited by 583 · cited 12×
“For Mobiact, Motionsense, and PAMAP2, the increase is around 4% whereas for MHEALTH, it is over 10%.”
BackgroundMethodInfluentialvq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
Baevski, A., Schneider, S., & Auli, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.05453 · Cited by 388 · cited 1×
“Similar to [15], [38], we propose to instead utilize multiple causal convolution blocks to perform the autoregressive summarization, due to its simplicity, faster training times, and ease of parallelization that recurrent models”
MethodExploring Simple Siamese Representation Learning
Chen, X., & He, K. (2020) · arXiv · doi:10.48550/arxiv.2011.10566 · Cited by 381
Wearable Activity Tracking in Car Manufacturing
Stiefmeier, T., Roggen, D., Ogris, G., Lukowicz, P., & Tr, G. (2008) · IEEE Pervasive Computing · doi:10.1109/mprv.2008.40 · Cited by 367 · cited 1×
“formed, has a multitude of applications, including health [1]– [3], industry [4]–[6], and fitness tracking [7], [8].”
BackgroundAn Unsupervised Autoregressive Model for Speech Representation Learning
Chung, Y.-A., Hsu, W.-N., Tang, H., & Glass, J. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-1473 · Cited by 357
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 7×
“Multi-task self supervision [19] first introduced selfsupervised learning to human activity recognition from sensor data.”
BackgroundMethodInfluentialFeature Learning for Activity Recognition in Ubiquitous Computing
Plötz, T., Hammerla, N., & Olivier, P. (2011) · Newcastle University · doi:10.25405/ncl.34175319 · Cited by 337
Self-citationWilletts, M., Hollowell, S., Aslett, L., Holmes, C., & Doherty, A. (2018) · Scientific Reports · doi:10.1038/s41598-018-26174-1 · Cited by 250 · cited 1×
“A Vicon Actigraph wearable camera was utilized for post-hoc labeling, resulting in around 2,500 hours of coarsely labeled data and six broad labels [40], namely sleep, sit-stand, mixed, walking, vehicle, and bicycling, as well as 200 fine-grained activities.”
MethodQFLan: A Tool for the Quantitative Analysis of Highly Reconfigurable Systems
Vandin, A., ter Beek, M. H., Legay, A., & Lluch Lafuente, A. (2018) · EasyChair Preprints · doi:10.29007/1mjd · Cited by 196
Protecting sensory data against sensitive inferences
Malekzadeh, M., Clegg, R. G., Cavallaro, A., & Haddadi, H. (2018) · Spiral (Imperial College London) · Cited by 166
Generative Pre-Training for Speech with Autoregressive Predictive Coding
Chung, Y.-A., & Glass, J. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9054438 · Cited by 157
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 11×
“For Mobiact, Motionsense, and PAMAP2, the increase is around 4% whereas for MHEALTH, it is over 10%.”
MethodInfluentialKwon, H., Tong, C., Haresamudram, H., Gao, Y., Abowd, G. D., Lane, N. D., & Plötz, T. (2020) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3411841 · Cited by 152
Self-citationContrastive 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 9×
“We investigate enhancements to components of the current CPC setup in the field of sensor-based HAR [21].”
BackgroundMethodInfluentialSelf-citationMasked 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 3×
“, Autoencoders [23] and Masked reconstruction [20]), which may not perform well under distribution shifts [27].”
BackgroundMethodSelf-citationTime Series Change Point Detection with Self-Supervised Contrastive Predictive Coding
Deldari, S., Smith, D. V., Xue, H., & Salim, F. D. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3449903 · Cited by 136 · cited 1×
“In this paper, we focus on the Contrastive Predictive Coding framework, which has been utilized for tasks such as representation learning [21] and change point detection [25] on wearable sensor datasets.”
MethodColloSSL: 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
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 10×
“As in [27], the learning rate during classification is decayed by 0.”
BackgroundMethodInfluentialSelf-citationDeep Learning for Human Activity Recognition in Mobile Computing
Plotz, T., & Guan, Y. (2018) · Computer · doi:10.1109/mc.2018.2381112 · Cited by 99 · cited 1×
“However, annotating this data is not as straightforward because it is typically considered privacy invasive, cumbersome, and sometimes simply impossible from a logistical perspective [10].”
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
Human Daily Activity and Fall Recognition Using a Smartphone’s Acceleration Sensor
Chatzaki, C., Pediaditis, M., Vavoulas, G., & Tsiknakis, M. (2017) · Communications in Computer and Information Science · doi:10.1007/978-3-319-62704-5_7 · Cited by 91 · cited 1×
“The datasets include: HHAR [40], Myogym [41] at the wrist, Mobiact (v2) [42], Motionsense [43] at the waist, and MHEALTH [8], PAMAP2”
MethodPrediction of Mood Instability with Passive Sensing
Morshed, M. B., Saha, K., Li, R., D'Mello, S. K., De Choudhury, M., Abowd, G. D., & Plötz, T. (2019) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3351233 · Cited by 91 · cited 1×
“Sensor-based Human Activity Recognition (HAR), which involves the automatic prediction of activities being performed, has a multitude of applications, including health [1]– [3], industry [4]–[6], and fitness tracking [7], [8].”
BackgroundSelf-citationOn the role of features in human activity recognition
Haresamudram, H., Anderson, D. V., & Plötz, T. (2019) · Proceedings of the 23rd International Symposium on Wearable Computers · doi:10.1145/3341163.3347727 · Cited by 90 · cited 4×
“Traditional approaches for unsupervised representation learning include Restricted Boltzmann Machines (RBMs) [22] and varieties of Autoencoders, such as Vanilla, Convolutional, or Recurrent Autoencoders [23], [29].”
BackgroundMethodInfluentialSelf-citationExploring 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
WearBreathing: Real World Respiratory Rate Monitoring Using Smartwatches
Liaqat, D., Abdalla, M., Abed-Esfahani, P., Gabel, M., Son, T., Wu, R., Gershon, A., Rudzicz, F., & Lara, E. D. (2019) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3328927 · Cited by 58
Improved Speech Representations with Multi-Target Autoregressive Predictive Coding
Chung, Y.-A., & Glass, J. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.213 · Cited by 58
Improved Speech Representations with Multi-Target Autoregressive Predictive CodingPreprint
Chung, Y.-A., & Glass, J. R. (2020) · Annual Meeting of the Association for Computational Linguistics · doi:10.48550/arxiv.2004.05274 · Cited by 58
MyoGym: introducing an open gym data set for activity recognition collected using myo armband
Koskimäki, H., Siirtola, P., & Röning, J. (2017) · Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers · doi:10.1145/3123024.3124400 · Cited by 46
An Unsupervised Autoregressive Model for Speech Representation LearningPreprint
Chung, Y.-A., Hsu, W.-N., Tang, H., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.03240 · Cited by 45
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
Yoshimura, N., Maekawa, T., Hara, T., Wada, A., & Namioka, Y. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3534572 · Cited by 38
Sense and Learn: Self-supervision for omnipresent sensors
Saeed, A., Ungureanu, V., & Gfeller, B. (2021) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100152 · Cited by 34
Morales, J., Yoshimura, N., Xia, Q., Wada, A., Namioka, Y., & Maekawa, T. (2022) · IEEE International Conference on Pervasive Computing and Communications · doi:10.1109/percom53586.2022.9762388 · Cited by 29
Morshed, M. B., Haresamudram, H., Bandaru, D., Abowd, G. D., & Plötz, T. (2022) · ACM International Symposium on Wearable Computers (ISWC) · doi:10.1145/3544794.3558469 · Cited by 17
Self-citationKwon, H., Tong, C., Haresamudram, H., Gao, Y., Abowd, G. D., Lane, N. D., & Ploetz, T. (2020) · arXiv · doi:10.48550/arxiv.2006.05675 · Cited by 14
Self-citationWilletts, M., Hollowell, S., Aslett, L. J. M., Holmes, C. C., & Doherty, A. (2017) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/187625 · Cited by 12
Generative Pre-Training for Speech with Autoregressive Predictive CodingPreprint
Chung, Y.-A., & Glass, J. R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.12607 · Cited by 10
Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using WearablesPreprint
Varamin, A. A., Abbasnejad, E., Shi, Q., Ranasinghe, D. C., & Rezatofighi, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08127 · Cited by 3
wav2vec: Unsupervised Pre-training for Speech Recognition
Schneider, S., Baevski, A., Collobert, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1904.05862
Untitled work
(2012) · doi:10.5555/2503308.2188395
Untitled work
Srivastava (2014) · doi:10.5555/2627435.2670313
Research works printed but not linked: 1
- 10.5555/3495724.3497510 · doi:10.5555/3495724.3497510
Cited by
Consequential Advancements of Self-Supervised Learning (SSL) in Deep Learning Contexts
Abdulrazzaq, M. M., Ramaha, N. T. A., Hameed, A. A., Salman, M., Yon, D. K., Fitriyani, N. L., Syafrudin, M., & Lee, S. W. (2024) · Mathematics · doi:10.3390/math12050758 · Cited by 74
“SimSiam employs a pair of mirror-image networks and a predictor network at the end of a node [62–64].”
Cross-Domain HAR: Few Shot Transfer Learning for Human Activity Recognition
Thukral, M., Haresamudram, H., & Ploetz, T. (2023) · arXiv · doi:10.48550/arxiv.2310.14390 · Cited by 45
Self-citationCross-Domain HAR: Few-Shot Transfer Learning for Human Activity Recognition
Thukral, M., Haresamudram, H., & Plötz, T. (2025) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3704921 · Cited by 71
Self-citationHaresamudram, H., Tang, C. I., Suh, S., Lukowicz, P., & Plötz, T. (2025) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3729467 · Cited by 33
Self-citationSelf-supervised Learning for Accelerometer-based Human Activity Recognition: A Survey
Logacjov, A. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3699767 · Cited by 40
Metadata
- Authors
- Haresamudram, H., Essa, I., & Plötz, T.
- Affiliations
- Georgia Institute of Technology (US)
- Venue
- 2023 IEEE International Conference on Pervasive Computing and Communications (PerCom)
- Publisher
- IEEE
- Published
- 2023-03-13
- Pages
- 232-241
- ISSN
- 2474-249X (ISSN-L)
- OpenAlex
- W4366249647
- Semantic Scholar
- 9daaa66c335a09be573fb5a1f6e133c4cbdd07c1
- Cited by
- 27
- References
- 63
- Citations by year
- 2026: 4 · 2025: 8 · 2024: 13 · 2023: 2
- FWCI
- 2.88
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE International Conference on Pervasive Computing and Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- contrastive predictive coding, human activity recognition, wearable sensors, self-supervised learning, unlabeled data, encoder architecture, 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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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.