Metraipolis › archive › dc_4b20da5d8a90
Foundation models for movement data: Are they ready for prime-time? — arXiv:2608.13316
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13316
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:27:55.798Z
- SHA-256 of the archived text
e05169e669b6c9a89928cb50cb81c25798fa637d6e5f541897e4086a228b2bd9- Stable URL of this page
https://metraipolis.com/documento/dc_4b20da5d8a90
How to cite
Foundation models for movement data: Are they ready for prime-time? — arXiv:2608.13316 — arXiv (en), https://arxiv.org/abs/2608.13316 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4b20da5d8a90 (Metraipolis archive dc_4b20da5d8a90, sha256 e05169e669b6c9a89928cb50cb81c25798fa637d6e5f541897e4086a228b2bd9)
BibTeX
@misc{dc4b20da5d8a90,
title = {Foundation models for movement data: Are they ready for prime-time? — arXiv:2608.13316},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13316},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4b20da5d8a90; sha256 e05169e669b6c9a89928cb50cb81c25798fa637d6e5f541897e4086a228b2bd9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13316. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Foundation models (FMs) trained on large-scale accelerometer data have been proposed as general-purpose feature extractors for health monitoring, but systematic evidence of their advantages is lacking. We present the first comprehensive evaluation of four open-source accelerometer FMs against supervised baselines covering 19 tasks across the domains of activity recognition including activities of daily living, clinical monitoring, and physiological inference. We find task-dependent performance results: supervised models remain competitive with FMs on human action recognition (HAR), with no consistent advantage for either, while selected FMs lead on fall and stress detection and are the most robust to sensor-placement variation. As frozen feature extractors, FMs are strongest for demographic inference, whereas sleep staging performance remains near chance level for all models. The internal FM representations show strong similarity across layers, highlighting potential for future FM improvements. Linear and frozen probing reveals that UniMTS provides the strongest representations and is the only FM that surpasses the supervised baselines without finetuning. Concept discovery analysis shows all models capture high-intensity activities clearly but struggle with sedentary, complex or ambiguous activities. We provide scenario-based deployment recommendations. Furthermore, we identify FM-derived activity profile inference-moving beyond fixed category classification-as a promising research direction. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG). Categorie arXiv: Signal Processing (eess.SP) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.13316 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T04:20:35.913Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).