Publications

@article{2022-Haresamudram-ASSHARUW,

title = {Assessing the State of Self-Supervised Human Activity Recognition using Wearables},

author = {Harish Haresamudram and Irfan Essa and Thomas Ploetz},

url = {https://dl.acm.org/doi/10.1145/3550299

https://arxiv.org/abs/2202.12938

https://arxiv.org/pdf/2202.12938

},

doi = {doi.org/10.1145/3550299},

year  = {2022},

date = {2022-09-07},

urldate = {2022-09-07},

booktitle = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)},

journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT)},

volume = {6},

number = {116},

issue = {3},

pages = {1–47},

publisher = {ACM},

abstract = {The emergence of self-supervised learning in the field of wearables-based human activity recognition (HAR) has opened up opportunities to tackle the most pressing challenges in the field, namely to exploit unlabeled data to derive reliable recognition systems for scenarios where only small amounts of labeled training samples can be collected. As such, self-supervision, i.e., the paradigm of 'pretrain-then-finetune' has the potential to become a strong alternative to the predominant end-to-end training approaches, let alone hand-crafted features for the classic activity recognition chain. Recently a number of contributions have been made that introduced self-supervised learning into the field of HAR, including, Multi-task self-supervision, Masked Reconstruction, CPC, and SimCLR, to name but a few. With the initial success of these methods, the time has come for a systematic inventory and analysis of the potential self-supervised learning has for the field. This paper provides exactly that. We assess the progress of self-supervised HAR research by introducing a framework that performs a multi-faceted exploration of model performance. We organize the framework into three dimensions, each containing three constituent criteria, such that each dimension captures specific aspects of performance, including the robustness to differing source and target conditions, the influence of dataset characteristics, and the feature space characteristics. We utilize this framework to assess seven state-of-the-art self-supervised methods for HAR, leading to the formulation of insights into the properties of these techniques and to establish their value towards learning representations for diverse scenarios.



},

keywords = {activity recognition, IMWUT, ubiquitous computing, wearable computing},

pubstate = {published},

tppubtype = {article}

}

@article{2021-Haresamudram-CPCHAR,

title = {Contrastive Predictive Coding for Human Activity Recognition},

author = {Harish Haresamudram and Irfan Essa and Thomas Ploetz},

url = {https://doi.org/10.1145/3463506

https://arxiv.org/abs/2012.05333},

doi = {10.1145/3463506},

year  = {2021},

date = {2021-06-01},

urldate = {2021-06-01},

booktitle = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},

journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},

volume = {5},

number = {2},

pages = {1--26},

abstract = {Feature extraction is crucial for human activity recognition (HAR) using body-worn movement sensors. Recently, learned representations have been used successfully, offering promising alternatives to manually engineered features. Our work focuses on effective use of small amounts of labeled data and the opportunistic exploitation of unlabeled data that are straightforward to collect in mobile and ubiquitous computing scenarios. We hypothesize and demonstrate that explicitly considering the temporality of sensor data at representation level plays an important role for effective HAR in challenging scenarios. We introduce the Contrastive Predictive Coding (CPC) framework to human activity recognition, which captures the long-term temporal structure of sensor data streams. Through a range of experimental evaluations on real-life recognition tasks, we demonstrate its effectiveness for improved HAR. CPC-based pre-training is self-supervised, and the resulting learned representations can be integrated into standard activity chains. It leads to significantly improved recognition performance when only small amounts of labeled training data are available, thereby demonstrating the practical value of our approach.},

keywords = {activity recognition, IMWUT, machine learning, ubiquitous computing},

pubstate = {published},

tppubtype = {article}

}