Metraipolis › archive › dc_7293c7a67a21

IMUDINO: Self-distilled Foundation Model for Inertial Sensing — arXiv:2611.07437

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.07437
License (as archived): CC0-1.0
Archived: 2026-11-06T14:42:22.863Z
SHA-256 of the archived text: 1c9ff3b8887074bbd8451a0f96570ec48f8be5f487935de442d20ff7fe05fe8d
Stable URL of this page: https://metraipolis.com/documento/dc_7293c7a67a21

How to cite

IMUDINO: Self-distilled Foundation Model for Inertial Sensing — arXiv:2611.07437 — arXiv (en), https://arxiv.org/abs/2611.07437 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7293c7a67a21 (Metraipolis archive dc_7293c7a67a21, sha256 1c9ff3b8887074bbd8451a0f96570ec48f8be5f487935de442d20ff7fe05fe8d)

BibTeX

@misc{dc7293c7a67a21,
  title = {IMUDINO: Self-distilled Foundation Model for Inertial Sensing — arXiv:2611.07437},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07437},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7293c7a67a21; sha256 1c9ff3b8887074bbd8451a0f96570ec48f8be5f487935de442d20ff7fe05fe8d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07437. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present IMUDINO, the first foundation model (FM) for inertial sensing to achieve competitive performance across diverse sensing tasks including human activity recognition (HAR), health, motion capture, and odometry. Prior inertial FMs often focus on one subfield of inertial sensing and sometimes underperform state-of-the-art supervised methods (e.g., in HAR), making their scope considerably narrower than FMs for vision and natural language. Moreover, they often require fixed input length and sampling rate, and generalize poorly to unseen sensor locations. To build a general-purpose foundation model for inertial sensing, we adapt the DINO self-supervised learning (SSL) paradigm to inertial data through a set of semantics-preserving motion transformations that simulate variations in motion pattern and sensor setup. For model architecture, we use a plain transformer encoder with frequency-aware positional encoding that natively supports varying input length and sampling rate. This simple setup proved remarkably effective for learning global and dense features generalizable across users, sensor setups, tasks, and, in the case of robot odometry, embodiments. We hope IMUDINO can serve as a backbone for inertial sensing and kickstart the development of general-purpose inertial FMs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.07437 — 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 2026-11-06T14:18:42.675Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).