ChatPPG.
Paper

Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts

Seungyeol Baek, Yoonbyung Chai, Yonghyeon Lee, Sungjoon Choi, Sungho Suh
arXiv preprint2026IMU
Read paper arXiv Cite
Published articleFirst posted: Aug 16, 2026Publication date: Oct 10, 2026Added to atlas: Oct 12, 2026Source
Citations0Crossref referencesChecked Oct 16, 2026
GitHub stars—Not available
HF downloads—Not available

Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.

TRI-HAR builds rotation invariance into multi-IMU activity recognition, so each sensor can be mounted at a different orientation. On four multi-IMU benchmarks it kept macro-F1 under such rotations and beat rotation-augmented baselines without needing rotation augmentation.

  • Signals: multi-location IMU
  • Property: structural invariance to per-location SO(3) rotations
  • Evaluation: 4 multi-IMU benchmarks
At a glance
Venue
arXiv preprint
Published
2026
DOI
10.1145/3830727.3834824 (opens in a new tab)
arXiv
2608.15621 (opens in a new tab)
PMID
Not reported
Licence
Not reported
Signals
IMU
Form factor
Not reported
Subjects
Not reported
Code
Not reported
Added
Oct 12, 2026

Abstract

Human Activity Recognition (HAR) with self-administered wearables, such as at-home rehabilitation and exercise monitoring, often requires reattaching inertial measurement units (IMUs) across sessions. In multi-IMU settings, this can induce independent orientation offsets across body locations, a deployment shift that conventional scalar HAR models do not structurally handle. Existing remedies rely on rotation augmentation, whose robustness depends on sampled transformations, or calibration and orientationnormalization pipelines requiring additional reference-frame assumptions or explicit procedures. We present Truly Rotation-Invariant HAR (TRI-HAR), a rotation-invariant framework that makes robustness to independent per-location IMU orientation offsets a structural model property. TRI-HAR reshapes accelerometer and gyroscope streams into triaxial vectors, applies a shared SO(3)-equivariant backbone and invariant projection to each IMU location, and fuses the resulting invariant features for activity classification. Across four multi-IMU benchmarks, TRI-HAR preserves macro-F1 under fixed independent per-location SO(3) rotations and outperforms rotation-augmented baselines under this target shift without requiring rotational augmentation.

Verbatim fromarXiv· arXiv metadata (abstracts are released under CC0)

Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts: ChatPPG research summary card

How it works

How Method works: Setup → Method → ResultSetup: Signals (multi-location IMU). Method: Method. Result: Evaluation (4 multi-IMU benchmarks).SetupSignals: multi-location IMUSignalsmulti-location IMUMethodMethodResultEvaluation: 4 multi-IMU benchmarksEvaluation4 multi-IMU benchmarks

Cite

@article{triharrotationinvariantm2026,
  title = {{Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts}},
  author = {Seungyeol Baek and Yoonbyung Chai and Yonghyeon Lee and Sungjoon Choi and Sungho Suh},
  year = {2026},
  journal = {arXiv preprint},
  doi = {10.1145/3830727.3834824},
  eprint = {2608.15621}
}

History

  1. Added to the ChatPPG research hub

More on ChatPPG