Metraipolis › archive › dc_bf521cbcf02f
MorphCL: Morphological Contrastive Learning for Inertial-based Human Activity Recognition — arXiv:2610.10245
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10245
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:55:45.779Z
- SHA-256 of the archived text
72e13a3037dbfc542bf0fc1ed73feddf288e7ad07dc8e287286f262ae1fcb32f- Stable URL of this page
https://metraipolis.com/documento/dc_bf521cbcf02f
How to cite
MorphCL: Morphological Contrastive Learning for Inertial-based Human Activity Recognition — arXiv:2610.10245 — arXiv (en), https://arxiv.org/abs/2610.10245 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf521cbcf02f (Metraipolis archive dc_bf521cbcf02f, sha256 72e13a3037dbfc542bf0fc1ed73feddf288e7ad07dc8e287286f262ae1fcb32f)
BibTeX
@misc{dcbf521cbcf02f,
title = {MorphCL: Morphological Contrastive Learning for Inertial-based Human Activity Recognition — arXiv:2610.10245},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10245},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf521cbcf02f; sha256 72e13a3037dbfc542bf0fc1ed73feddf288e7ad07dc8e287286f262ae1fcb32f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10245. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Despite the ubiquity of sensors in wearable and mobile devices and the abundance of human movement data they generate, translating unlabeled recordings into foundational motion models remains an open challenge. Self-supervised learning (SSL) has alleviated the need for costly annotations, yet existing approaches leave the global structure of large-scale motion data largely untapped, relying on randomly sampled batches and local comparisons that become particularly problematic for in-the-wild inertial data dominated by stationary, low-variance behaviors. Here we introduce Morphological Contrastive Learning (MorphCL), a self-supervised pretraining framework that uses structure-aware grouping to inject explicit modeling of global structure into inertial-based SSL approaches. Building on two well-established pillars of motion analysis, the discovery of motion primitives, or motifs, and domain-specific feature descriptors, we show that MorphCL substantially improves linear probing and finetuning results of learned encoders by up to 15 percentage points in F1-score. In a comparison with existing foundation models, we demonstrate that MorphCL-pretrained encoders match or surpass them models in linear probing performance while trained on $4600\times$ less data. Qualitative analysis of the resulting embedding spaces further reveals morphologically meaningful cluster structure, with improved separation of kinematically similar activity classes. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.HC, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2610.10245 — 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 2026-10-08T10:50:22.571Z dalla pagina https://arxiv.org/list/cs.HC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).