REACT: A Conditioning Framework for User-Adaptive sEMG Hand Pose Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Eric, Cheung, Hei Shing
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916061710909440
author Xie, Eric
Cheung, Hei Shing
author_facet Xie, Eric
Cheung, Hei Shing
contents Surface electromyography (sEMG) enables continuous hand pose estimation on wearable devices, but models trained on multi-user corpora degrade on unseen individuals due to inter-user variability in anatomy and electrode placement. We propose REACT, a lightweight conditioning framework that personalizes a frozen pretrained EMG-to-pose backbone at inference time using only a handful of calibration recordings. REACT learns a compact user embedding from calibration data and applies Feature-wise Linear Modulation (FiLM) to adapt the shared encoder's feature space, requiring no gradient updates at deployment. On the large-scale EMG2POSE benchmark, REACT improves over the state-of-the-art baseline across all three generalization splits in both regression and tracking modes, reducing angular error by up to 3.9% with minimal parameter overhead and under 45 seconds of per-user calibration.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30127
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle REACT: A Conditioning Framework for User-Adaptive sEMG Hand Pose Estimation
Xie, Eric
Cheung, Hei Shing
Human-Computer Interaction
Signal Processing
Surface electromyography (sEMG) enables continuous hand pose estimation on wearable devices, but models trained on multi-user corpora degrade on unseen individuals due to inter-user variability in anatomy and electrode placement. We propose REACT, a lightweight conditioning framework that personalizes a frozen pretrained EMG-to-pose backbone at inference time using only a handful of calibration recordings. REACT learns a compact user embedding from calibration data and applies Feature-wise Linear Modulation (FiLM) to adapt the shared encoder's feature space, requiring no gradient updates at deployment. On the large-scale EMG2POSE benchmark, REACT improves over the state-of-the-art baseline across all three generalization splits in both regression and tracking modes, reducing angular error by up to 3.9% with minimal parameter overhead and under 45 seconds of per-user calibration.
title REACT: A Conditioning Framework for User-Adaptive sEMG Hand Pose Estimation
topic Human-Computer Interaction
Signal Processing
url https://arxiv.org/abs/2605.30127