ChatPPG.
Join free
First page or project page of “GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment (Cai & Hong; arXiv 2611.01684)” (opens in a new tab)

PaperarXiv:2611.01684

GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment (Cai & Hong; arXiv 2611.01684)

Preprint2026Added Nov 5, 2026

Authors: Yize Cai, Zhiqing Hong (corresponding)

arXiv 2611.01684v1 (cs.CV, 2026-11-01); CC BY 4.0

PDF (opens in a new tab) arXiv2611.01684 (opens in a new tab) Code · GaitFMsaiketa/GaitFM (opens in a new tab) Cite
Open code
First page or project page of “GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment (Cai & Hong; arXiv 2611.01684)” (opens in a new tab)

Cai, Yize et al., "GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment", arXiv:2611.01684, CC BY 4.0

TL;DR

Inputs: 5 s windows at 50 Hz; gyro channels masked with p=0.5 so accel-only input is supported. Pretraining corpus: GSTRIDE, FoGContest, COMPWALK-ACL, mPower, WearGait-PD, Mobilise-D, ClinicalGait. External validation: LTMM, FoG-STAR, StrokeRehabilitation, GaitPrint.

  • Form factor: multi-site (lower back, feet, ankles, wrist, phone)

Abstract

Gait assessment supports the diagnosis, monitoring, and prognosis of diverse movement-related conditions, such as neurological and musculoskeletal disorders. Recent advances in deep learning using everyday wearable inertial measurement units (IMUs) offer an accessible and low-cost approach to automated gait assessment. However, IMU measurements vary substantially across individuals, body locations, and device configurations, while existing deep learning models are typically developed using small, homogeneous datasets for specific clinical tasks, limiting their robustness and generalizability in diverse real-world contexts. Here we present GaitFM, a cross-modal foundation model for gait assessment using IMU sensors. GaitFM improves the generalizability of gait assessment by transferring knowledge from large vision models and pretraining on unlabeled IMU sensor data. We pretrain GaitFM on a large curated dataset comprising about 4,000 participants and 1.23 million gait windows across diverse clinical and daily conditions, sensor modalities, and body locations. GaitFM demonstrates strong performance across 18 gait-related tasks, including 3 gait parameter estimation tasks, 14 disease and gait abnormality detection tasks, and 1 clinical outcome prediction task. Furthermore, GaitFM generalizes across different sensor configurations and body locations, including those commonly used in clinical settings and everyday wearable devices. These findings demonstrate the effectiveness of transferring visual knowledge in improving sensor-based gait assessment performance, offering a new promising pathway for addressing data scarcity in the sensor and medical domains.

Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Tasks

Activity recognition

Signals

IMU

Keywords

GaitMAEViTCross ModalImage InitParkinsonFoGStroke

Datasets used

Models

How it works

How GaitFM works: Setup → Method → TargetSetup: Signals (acc, gyro); Form factor (multi-site (lower back, feet, ankles, wrist, phone)). Method: GaitFM (Transformer · Masked reconstruction). Target: Activity recognition.SetupSignals: acc, gyroxyzSignalsacc, gyroForm factor: multi-site (lower back, feet, ankles, wrist, phone)Form factormulti-site (lower back, feet, ankles…Method×NGaitFMTransformer · Masked reconstructionTargetActivity recognitionActivity recognition

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Cai, Y., & Hong, Z. (2026). GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment (Cai & Hong; arXiv 2611.01684). arXiv 2611.01684v1. https://arxiv.org/abs/2611.01684
Cai, Yize and Zhiqing Hong. 2026. "GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment (Cai & Hong; arXiv 2611.01684)." arXiv 2611.01684v1. https://arxiv.org/abs/2611.01684.
Cai, Y. and Hong, Z. (2026) 'GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment (Cai & Hong; arXiv 2611.01684)', arXiv 2611.01684v1. Available at: https://arxiv.org/abs/2611.01684
Cai, Yize, and Zhiqing Hong "GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment (Cai & Hong; arXiv 2611.01684)." arXiv 2611.01684v1, 2026. https://arxiv.org/abs/2611.01684.
Y. Cai and Z. Hong, "GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment (Cai & Hong; arXiv 2611.01684)," arXiv 2611.01684v1, 2026, [Online]. Available: https://arxiv.org/abs/2611.01684.
@misc{cai2026gaitfm,
  title         = {{GaitFM: A Cross-Modal Foundation Model for Wearable Gait Assessment (Cai \& Hong; arXiv 2611.01684)}},
  author        = {Cai, Yize and Hong, Zhiqing},
  year          = {2026},
  howpublished  = {arXiv 2611.01684v1},
  eprint        = {2611.01684},
  archivePrefix = {arXiv}
}

Source metadata: 2026

Record updated Nov 5, 2026

Added to the ChatPPG research hub

Same tasks, data and authors

Papers

Models

Datasets