Zobrazeno 1 - 10
of 739
pro vyhledávání: '"P. Spathis"'
Contrastive learning (CL) has emerged as a promising approach for representation learning in time series data by embedding similar pairs closely while distancing dissimilar ones. However, existing CL methods often introduce false negative pairs (FNPs
Externí odkaz:
http://arxiv.org/abs/2410.10048
Autor:
Yfantidou, Sofia, Spathis, Dimitris, Constantinides, Marios, Vakali, Athena, Quercia, Daniele, Kawsar, Fahim
Self-supervised learning (SSL) has become the de facto training paradigm of large models, where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Despite demonstrating comparable performance with supervised met
Externí odkaz:
http://arxiv.org/abs/2406.02361
Autor:
Spathis, Dimitris, Saeed, Aaqib, Etemad, Ali, Tonekaboni, Sana, Laskaridis, Stefanos, Deldari, Shohreh, Tang, Chi Ian, Schwab, Patrick, Tailor, Shyam
This non-archival index is not complete, as some accepted papers chose to opt-out of inclusion. The list of all accepted papers is available on the workshop website.
Externí odkaz:
http://arxiv.org/abs/2403.10561
Wearable technologies enable continuous monitoring of various health metrics, such as physical activity, heart rate, sleep, and stress levels. A key challenge with wearable data is obtaining quality labels. Unlike modalities like video where the vide
Externí odkaz:
http://arxiv.org/abs/2401.14107
Autor:
Tang, Chi Ian, Qendro, Lorena, Spathis, Dimitris, Kawsar, Fahim, Mathur, Akhil, Mascolo, Cecilia
Wearable-based Human Activity Recognition (HAR) is a key task in human-centric machine learning due to its fundamental understanding of human behaviours. Due to the dynamic nature of human behaviours, continual learning promises HAR systems that are
Externí odkaz:
http://arxiv.org/abs/2401.02255
Autor:
Yfantidou, Sofia, Spathis, Dimitris, Constantinides, Marios, Vakali, Athena, Quercia, Daniele, Kawsar, Fahim
Self-supervised learning (SSL) has become the de facto training paradigm of large models where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Hypothesizing that SSL models would learn more generic, hence les
Externí odkaz:
http://arxiv.org/abs/2401.01640
Publikováno v:
Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing & the 2023 ACM International Symposium on Wearable Computing (UbiComp/ISWC '23 Adjunct )
How can we ensure that Ubiquitous Computing (UbiComp) research outcomes are both ethical and fair? While fairness in machine learning (ML) has gained traction in recent years, fairness in UbiComp remains unexplored. This workshop aims to discuss fair
Externí odkaz:
http://arxiv.org/abs/2309.12877
Autor:
Spathis, Dimitris, Kawsar, Fahim
Large Language Models (LLMs) have demonstrated remarkable generalization across diverse tasks, leading individuals to increasingly use them as personal assistants and universal computing engines. Nevertheless, a notable obstacle emerges when feeding
Externí odkaz:
http://arxiv.org/abs/2309.06236
Autor:
Joseph David Clark, Kate Binnie, Maddie Bond, Michael Crooks, David C. Currow, Jordan Curry, Helen Elsey, Monsur Habib, Ann Hutchinson, Ireneous Soyiri, Miriam J. Johnson, Shreya Nair, Seema Rao, Noemia Siqueira-Filha, Anna Spathis, Siân Williams
Publikováno v:
npj Primary Care Respiratory Medicine, Vol 34, Iss 1, Pp 1-5 (2024)
It is likely that the burden of breathlessness in low and middle-income countries (LMICs) is much higher than has been estimated using calculations of disease burden and expected prevalence of the symptom. However, most breathlessness research has be
Externí odkaz:
https://doaj.org/article/f8459e45e2da4098afb7b9d4b99137fd
Autor:
Deldari, Shohreh, Spathis, Dimitris, Malekzadeh, Mohammad, Kawsar, Fahim, Salim, Flora, Mathur, Akhil
Limited availability of labeled data for machine learning on multimodal time-series extensively hampers progress in the field. Self-supervised learning (SSL) is a promising approach to learning data representations without relying on labels. However,
Externí odkaz:
http://arxiv.org/abs/2307.16847