mlsanityData to 7 Oct 2026

Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram

arXiv 2402.09450 ↗First posted 2 Feb 2024eess.SP cs.AI cs.LGcited by 84

Not on the map. Why?

Abstract (arXiv)

Electrocardiograms (ECG) are widely employed as a diagnostic tool for monitoring electrical signals originating from a heart. Recent machine learning research efforts have focused on the application of screening various diseases using ECG signals. However, adapting to the application of screening disease is challenging in that labeled ECG data are limited. Achieving general representation through self-supervised learning (SSL) is a well-known approach to overcome the scarcity of labeled data; however, a naive application of SSL to ECG data, without considering the spatial-temporal relationships inherent in ECG signals, may yield suboptimal results. In this paper, we introduce ST-MEM (Spatio-Temporal Masked Electrocardiogram Modeling), designed to learn spatio-temporal features by reconstructing masked 12-lead ECG data. ST-MEM outperforms other SSL baseline methods in various experimental settings for arrhythmia classification tasks. Moreover, we demonstrate that ST-MEM is adaptable to various lead combinations. Through quantitative and qualitative analysis, we show a spatio-temporal relationship within ECG data. Our code is available at https://github.com/bakqui/ST-MEM.

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Builds on 25 of its 53 references that are in the map. First posted on arXiv 2 Feb 2024.

Builds on

25 of 53 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  10. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  11. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  12. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 656
13 more
  1. 2020CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patientscited by 170
  2. 2019Automatic diagnosis of the 12-lead ECG using a deep neural networkcited by 164
  3. 2020Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XLcited by 158
  4. 2020Self-supervised ECG Representation Learning for Emotion Recognitioncited by 99
  5. 2023What Do Self-Supervised Vision Transformers Learn?cited by 90
  6. 2021Self-supervised representation learning from 12-lead ECG datacited by 80
  7. 2022Lead-agnostic Self-supervised Learning for Local and Global Representations of Electrocardiogramcited by 38
  8. 20213KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentationscited by 36
  9. 2021Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signalscited by 35
  10. 2018ECG arrhythmia classification using a 2-D convolutional neural networkcited by 17
  11. 2022Analysis of Augmentations for Contrastive ECG Representation Learningcited by 12
  12. 2023MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferringcited by 5
  13. 2020Data Augmentation for Electrocardiogram Classification with Deep Neural Networkcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 12; 2025: 28; 2026: 44.

84 papers.

Sort:

  1. 2024ECG-FM: An Open Electrocardiogram Foundation Modelcited by 89
  2. 2024Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancementcited by 66
  3. 2025Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Modelcited by 36
  4. 2024MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generationcited by 29
  5. 2024An Electrocardiogram Foundation Model Built on over 10 Million Recordings with External Evaluation across Multiple Domainscited by 27
  6. 2024Teach Multimodal LLMs to Comprehend Electrocardiographic Imagescited by 25
  7. 2025LSM-2: Learning from Incomplete Wearable Sensor Datacited by 20
  8. 2024Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecturecited by 17
  9. 2024Boosting Masked ECG-Text Auto-Encoders as Discriminative Learnerscited by 16
  10. 2025From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretrainingcited by 15
  11. 2024Self-Supervised Pre-Training with Joint-Embedding Predictive Architecture Boosts ECG Classification Performancecited by 14
  12. 2024ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modelingcited by 9
38 more
  1. 2025anyECG-chat: A Generalist ECG-MLLM for Flexible ECG Input and Multi-Task Understandingcited by 9
  2. 2024ECHOPulse: ECG controlled echocardio-grams video generationcited by 8
  3. 2025BenchECG and xECG: a benchmark and baseline for ECG foundation modelscited by 8
  4. 2026ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretationcited by 8
  5. 2026OSF: On Pre-training and Scaling of Sleep Foundation Modelscited by 8
  6. 2025CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Modelscited by 7
  7. 2025SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learningcited by 6
  8. 2025Benchmarking ECG FMs: A Reality Check Across Clinical Taskscited by 6
  9. 2024AnyECG: Foundational Models for Multitask Cardiac Analysis in Real-World Settingscited by 5
  10. 2025Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputscited by 5
  11. 2025Global and Local Contrastive Learning for Joint Representations from Cardiac MRI and ECGcited by 5
  12. 2025Self-Alignment Learning to Improve Myocardial Infarction Detection from Single-Lead ECGcited by 4
  13. 2024Translating Electrocardiograms to Cardiac Magnetic Resonance Imaging Useful for Cardiac Assessment and Disease Screening: A Multi-Center Studycited by 3
  14. 2025Interpretable Multimodal Zero-Shot ECG Diagnosis via Structured Clinical Knowledge Alignmentcited by 3
  15. 2026RhythmBERT: A Self-Supervised Language Model Based on Latent Representations of ECG Waveforms for Heart Disease Detectioncited by 3
  16. 2026CardioState-JEPA: Delay-Aware Cross-Modal Learning of a Shared Cardiac Representationcited by 3
  17. 2025FOCAL: Fine-Grained Optimal-Transport-Driven Contrastive Alignment of Language and ECGs with Waveform Enhancementcited by 2
  18. 2025Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Frameworkcited by 2
  19. 2025SemiSegECG: A Multi-Dataset Benchmark for Semi-Supervised Semantic Segmentation in ECG Delineationcited by 2
  20. 2025A Unified AI Approach for Continuous Monitoring of Human Health and Diseases from Intensive Care Unit to Home with Physiological Foundation Models (UNIPHY+)cited by 2
  21. 2025Fusion of ECG Foundation Model Embeddings to Improve Early Detection of Acute Coronary Syndromescited by 1
  22. 2025Enhancing Contrastive Learning-based Electrocardiogram Pretrained Model with Patient Memory Queuecited by 1
  23. 2025ECG-Soup: Harnessing Multi-Layer Synergy for ECG Foundation Modelscited by 1
  24. 2025Domain Knowledge is Power: Leveraging Physiological Priors for Self Supervised Representation Learning in Electrocardiographycited by 1
  25. 2025Tracing the Heart's Pathways: ECG Representation Learning from a Cardiac Conduction Perspectivecited by 1
  26. 2026Foundation Model for Cardiac Time Series via Masked Latent Attentioncited by 1
  27. 2026LVCG: Learning ECG Representations in the Latent Vectorcardiogram Spacecited by 1
  28. 2026Hierarchical Self-Supervised Representation Learning Framework for Multivariate Time Series Grounded in ECG Analysiscited by 1
  29. 2025CuPID: Leveraging Masked Single-Lead ECG Modelling for Enhancing the Representationscited by 0
  30. 2025Parallel-Learning of Invariant and Tempo-variant Attributes of Single-Lead Cardiac Signals: PLITAcited by 0
  31. 2025Multimodal Latent Fusion of ECG Leads for Early Assessment of Pulmonary Hypertensioncited by 0
  32. 2025Masked Autoencoders that Feel the Heart: Unveiling Simplicity Bias for ECG Analysescited by 0
  33. 2025A Language-Signal-Vision Multimodal Framework for Multitask Cardiac Analysiscited by 0
  34. 2025A Masked Representation Learning to Model Cardiac Functions Using Multiple Physiological Signalscited by 0
  35. 2025Bridging Performance Gaps for ECG Foundation Models: A Post-Training Strategycited by 0
  36. 2026BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Diagnosiscited by 0
  37. 2026ELF: A Family of Encoder-Free ECG-Language Modelscited by 0
  38. 2026Position: Evaluation of ECG Representations Must Be Fixedcited by 0

50 most cited of 84 All 84 (JSON)