Learning Generalizable Action Representations via Pre-training AEMG

• URL: http://arxiv.org/abs/2605.03462v1
• Date: Tue, 05 May 2026 07:50:00 GMT
• Title: Learning Generalizable Action Representations via Pre-training AEMG
• Abstract summary: We propose Any Electromyography (AEMG), the first large-scale, self-supervised representation learning framework for EMG.<n>AEMG reconceptualizes neuromuscular dynamics linguistically, utilizing a novel Neuromuscular Contraction Tokenizer (NCT) to translate discrete muscle contractions into structural words.<n> Experiments demonstrate that AEMG improves the zero-shot leave-one-subject-out (LOSO) accuracy by 5.79-9.25% compared to six state-of-the-art baselines.
• Score: 1.3478288753277627
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A fundamental role in decoding human motor intent and enabling intuitive human-computer interaction is played by electromyography (EMG). However, its generalization capability across subjects, devices, and tasks remains substantially limited by data heterogeneity, label scarcity, and the lack of a unified representational framework. To bridge this gap, we propose Any Electromyography (AEMG), the first large-scale, self-supervised representation learning framework for EMG. AEMG reconceptualizes neuromuscular dynamics linguistically, utilizing a novel Neuromuscular Contraction Tokenizer (NCT) to translate discrete muscle contractions into structural words and temporal activation patterns into coherent sentences. Furthermore, we compile the largest cross-device EMG signal vocabulary to date, enabling seamless transfer across arbitrary channel topologies and sampling rates. Experiments demonstrate that AEMG improves the zero-shot leave-one-subject-out (LOSO) accuracy by 5.79-9.25% compared to six state-of-the-art baselines, and achieves more than 90% few-shot adaptation performance with only 5% of target user data. Our work has proposed the concept of EMG signals as a cross-device physiological language, learned their grammar from massive amounts of data, and laid the groundwork for a single-training, universally applicable EMG foundation model.

Related papers

• CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings [6.409806752431095]
  Intracranial electrocorticography (ECoG) offers high-signal-to-noise access to cortical activity for brain-computer interfaces.<n>We investigate whether large pretrained scalp-EEG foundation models (EEG FMs) can be adapted to ECoG.<n>We introduce CORTEG, a cross-modality transfer framework that combines a pretrained EEG FM backbone, an electrode-aware KNNSoftFourier spatial adapter, and a dual-stream tokenizer for low-frequency and high-gamma activity.
  arXiv  Detail & Related papers  (2026-05-11T10:40:42Z)
• Decoding High-Dimensional Finger Motion from EMG Using Riemannian Features and RNNs [1.1534313664323634]
  We present an end-to-end framework for continuous EMG-to-kinematics regression using only consumer-grade hardware.<n>The framework combines an 8-channel EMG armband, a single webcam, and an automatic synchronization procedure.
  arXiv  Detail & Related papers  (2026-04-24T12:27:33Z)
• CAT-Net: A Cross-Attention Tone Network for Cross-Subject EEG-EMG Fusion Tone Decoding [0.8714814768600078]
  We propose a novel cross-subject multimodal BCI decoding framework.<n>It fuses EEG and EMG signals to classify four Mandarin tones under both audible and silent speech conditions.<n>Our findings suggest that tone-level decoding with minimal EEG-EMG channels is feasible and potentially generalizable across subjects.
  arXiv  Detail & Related papers  (2025-11-14T03:50:54Z)
• REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects [5.368295573908306]
  REVE (Representation for EEG with Versatile Embeddings) is a pretrained model explicitly designed to generalize across diverse EEG signals.<n>We pretrain REVE on over 60,000 hours of EEG data from 92 datasets spanning 25,000 subjects, representing the largest EEG pretraining effort to date.<n>We release code, pretrained weights, and tutorials to support standardized EEG research and accelerate progress in clinical neuroscience.
  arXiv  Detail & Related papers  (2025-10-24T15:52:46Z)
• MEG-GPT: A transformer-based foundation model for magnetoencephalography data [6.336623115095147]
  Recent advances in deep learning have enabled significant progress in other domains, such as language and vision, by using foundation models at scale.<n>Here, we introduce MEG-GPT, a transformer based foundation model that uses time-attention and next time-point prediction.<n>We trained MEG-GPT on tokenised brain region time-courses extracted from a large-scale MEG dataset.
  arXiv  Detail & Related papers  (2025-10-20T20:18:38Z)
• WaveMind: Towards a Conversational EEG Foundation Model Aligned to Textual and Visual Modalities [55.00677513249723]
  EEG signals simultaneously encode both cognitive processes and intrinsic neural states.<n>We map EEG signals and their corresponding modalities into a unified semantic space to achieve generalized interpretation.<n>The resulting model demonstrates robust classification accuracy while supporting flexible, open-ended conversations.
  arXiv  Detail & Related papers  (2025-09-26T06:21:51Z)
• CRIA: A Cross-View Interaction and Instance-Adapted Pre-training Framework for Generalizable EEG Representations [52.251569042852815]
  CRIA is an adaptive framework that utilizes variable-length and variable-channel coding to achieve a unified representation of EEG data across different datasets.<n>The model employs a cross-attention mechanism to fuse temporal, spectral, and spatial features effectively.<n> Experimental results on the Temple University EEG corpus and the CHB-MIT dataset show that CRIA outperforms existing methods with the same pre-training conditions.
  arXiv  Detail & Related papers  (2025-06-19T06:31:08Z)
• CodeBrain: Towards Decoupled Interpretability and Multi-Scale Architecture for EEG Foundation Model [52.466542039411515]
  EEG foundation models (EFMs) have emerged to address the scalability issues of task-specific models.<n>We present CodeBrain, a two-stage EFM designed to fill this gap.<n>In the first stage, we introduce the TFDual-Tokenizer, which decouples heterogeneous temporal and frequency EEG signals into discrete tokens.<n>In the second stage, we propose the multi-scale EEGSSM architecture, which combines structured global convolution with sliding window attention.
  arXiv  Detail & Related papers  (2025-06-10T17:20:39Z)
• BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals [46.121056431476156]
  This paper proposes Brain Omni, the first brain foundation model that generalises across heterogeneous EEG and MEG recordings.<n>Existing approaches typically rely on separate, modality- and dataset-specific models, which limits performance and cross-domain scalability.<n>A total of 1,997 hours of EEG and 656 hours of MEG data are curated and standardised from publicly available sources for pretraining.
  arXiv  Detail & Related papers  (2025-05-18T14:07:14Z)
• Geometry of orofacial neuromuscular signals: speech articulation decoding using surface electromyography [0.0]
  We present data and methods for decoding speech articulations using surface electromyogram (EMG) signals.<n>EMG-based speech neuroprostheses offer a promising approach for restoring audible speech in individuals who have lost the ability to speak intelligibly.
  arXiv  Detail & Related papers  (2024-11-04T20:31:22Z)
• TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation [65.65530016765615]
  We propose a hierarchical predictive coding framework that captures multi-scale dependencies through three complementary learning objectives.<n> TokenUnify integrates random token prediction, next-token prediction, and next-all token prediction to create a comprehensive representational space.<n>We also introduce a large-scale EM dataset with 1.2 billion annotated voxels, offering ideal long-sequence visual data with spatial continuity.
  arXiv  Detail & Related papers  (2024-05-27T05:45:51Z)
• CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion [49.1574468325115]
  A key aim in EEG analysis is to extract the underlying neural activation (content) as well as to account for the individual subject variability (style) Inspired by recent advancements in voice conversion technologies, we propose a novel contrastive split-latent permutation autoencoder (CSLP-AE) framework that directly optimize for EEG conversion.
  arXiv  Detail & Related papers  (2023-11-13T22:46:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.