Self-Supervised Time Series Representation Learning

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 333% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 91

All topics

T-JEPA: A Temporal Joint-Embedding Predictive Architecture for Learning Better Remote Sensing Representations
Oct 5, 2026Bowen Peng, Li Liu, Yongxiang Liu +3Geospatial Representation Learning Self-Supervised Time Series Representation Learning
National University of Defense Technology, Changsha, China
EMG-GPT: Predictive Pretraining on Residual-Quantized EMG Tokens for Hand Pose Estimation
Oct 4, 2026Ettore Magni, Rolandos Alexandros Potamias, Stefanos Zafeiriou +1Representation Learning Self-Supervised Time Series Representation Learning
Imperial College London
CORD: Learning Reusable Degradation Representations Across Heterogeneous Physical Systems
Sep 30, 2026Haibo Li, Zhiguo ZengRepresentation Learning Self-Supervised Time Series Representation Learning
CentraleSupélec, Université Paris-Saclay
WinoTS: Wavelet-based Self-Distillation for Time Series Models
Sep 30, 2026Noam Major, Kathy Razmadze, Yoli ShavitSelf-Supervised Time Series Representation Learning Time Series Data Augmentation
Bar-Ilan University, Ramat-Gan, Israel
Longer Records, Broader Invariance: The Hidden Scaling Problem in Longitudinal Contrastive Learning
Sep 29, 2026Rameen Mahmood, Xuhai "Orson" Xu, Zachary Beattie +2Contrastive Learning Self-Supervised Time Series Representation Learning
New York University · Columbia University · Oregon Health & Science University
Addressing Spatial Indistinguishability in Spatiotemporal Prediction via Optimal Transport-Guided Masking
Sep 28, 2026Guangyu Wang, Jiawei TongSelf-Supervised Time Series Representation Learning Spatiotemporal Forecasting
Data Science and Artificial Intelligence, Dongbei University of Finance and Economics, Dalian, Liaoning, China · Institute of Systems, Molecular & Integrative Biology, University of Liverpool, Liverpool, United Kingdom
A Hybrid CNN--State-Space--Attention Backbone with Joint-Embedding Predictive Pretraining for 12-Lead ECG Classification
Sep 24, 2026Yakoub Bazi, Sarah Aljuhani, Mohamad M. Al Rahhal +2Electrocardiography Self-Supervised Time Series Representation Learning
Computer Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh, 11543, Saudi Arabia · Applied Computer Science Department, College of Applied Computer Science, King Saud University, Riyadh, 11543, Saudi Arabia
Transferable Evidence Reconstruction for Longitudinal Glucose Representations
Sep 23, 2026Tian Zhou, Bingqing Peng, Linxiao Yang +6Representation Learning Self-Supervised Time Series Representation Learning
Ant Group · Independent Researcher
EMGBlend: Heterogeneity-Aware Self-Supervised Pretraining for Gesture and Force Decoding
Sep 22, 2026Yuwei Jia, Cheng Zhong, Jinyang Yu +1EMG-Based Gesture Recognition Self-Supervised Pre-Training
Beijing University of Posts and Telecommunications, China · Dexwise, China · Shenzhen University, China
FreqCondNorm: Towards Cross-domain Predictive Maintenance through a Frequency-Conditioned Transformer Foundation Model
Sep 17, 2026Zaynab Raounak, Camille LHermine, Zhiguo ZengMulti-Source Domain Adaptation Self-Supervised Time Series Representation Learning
Laboratoire Génie Industriel, CentraleSupélec, Université Paris-Saclay, France
Distributed JEPA: A Self-Supervised Framework for Energy Forecasting
Sep 15, 2026Liana Toderean, Tudor Cioara, Vasilis Michalakopoulos +3Self-Supervised Time Series Representation Learning Joint-Embedding Predictive Architecture
Distributed Systems Research Laboratory, Computer Science Department, Technical University of Cluj-Napoca, G. Barițiu 26-28, 400027 Cluj-Napoca, Romania · Decision Support Systems Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, Ir. Politechniou 9, 157 73 Athens, Greece
MANAS-2: Constrained Reconstruction for EEG Foundation Models
Sep 12, 2026Arvasu Kulkarni, Aditya Ray Mishra, Jeet Bandhu Lahiri +5Electroencephalography Masked Autoencoders
Mannas AI · Indian Institute of Technology, Mandi
DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended Version
Sep 7, 2026Sean Bin Yang, Hao Miao, Zongyi Xu +5Contrastive Learning Representation Learning
Aalborg University, Denmark · The Hong Kong Polytechnic University, Hong Kong · Chongqing Univeristy of Posts and Telecommunications, China +1
REFINE: Trajectory Representation Learning via Closed-Loop Transcription -- Extended Version
Sep 7, 2026Sean Bin Yang, Ying Sun, Jilin Hu +5Contrastive Learning Self-Supervised Time Series Representation Learning
Aalborg University Aalborg, Denmark · Chongqing Universtiy of Posts and Telecommunications Chongqing, China · East China Normal University Shanghai, China +1
CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting
Aug 20, 2026Alexander Marusov, Dmitry Anikin, Petr Sokerin +3Variational Autoencoders Multivariate Time Series Forecasting
Applied AI Institute Moscow, Russia
The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning
Aug 13, 2026Ahmed Sameh, Ramzi Al-Sharawi, Yogatheesan VaratharajahSelf-Supervised Time Series Representation Learning Electrocardiogram Foundation Models
Computer Science & Engineering, University of Minnesota Twin Cities, Minneapolis, MN 55455. · Robotics, University of Minnesota Twin Cities, Minneapolis, MN 55455.
Capturing Uncertainty in Human Motion for Representation Learning in Soccer
Aug 11, 2026Yizhou Xu, Lars Bretzner, Tiesheng Wang +1Self-Supervised Time Series Representation Learning Sports Video Analysis
KTH Royal Institute of Technology · EA Sports TRACAB
Is Self-Pretraining really useful to improve diagnosis in medical Time Series?
Aug 6, 2026Omar Coser, Antonio Orvieto, Paolo Soda +1Time Series Classification Self-Supervised Time Series Representation Learning
Unit of Artificial Intelligence & Computer Systems, Universit`a Campus Bio-Medico di Roma, Via ´Alvaro del Portillo, 21, Rome, 00128, Italy. · Unit of Advanced Robotics and Human-Centered Technologies, Universit`a Campus Bio-Medico di Roma, Via ´Alvaro del Portillo, 21, Rome, 00128, Italy. · Max Planck Institute for Intelligent Systems +2
Spectral Aliasing Pretext: A novel task for Self-Supervised fault diagnosis in rotating machinery
Aug 6, 2026Victor Gialis, Maxime Metz, David Esteve +1Self-Supervised Time Series Representation Learning Fault Diagnosis
LASPI, Univ. Jean Monnet, Roanne, 42300, France · Pellenc ST, Applied Research Group, Pertuis, 84120, France · LabCom Aioly, Artificial Intelligence and Optics Laboratory, Montpellier, 34196, France +1
EEG-JEPA: Structured Latent Prediction for EEG Foundation Models
Jul 31, 2026Jinhao Li, Zhiyuan Ma, Xueqiao Han +8Self-Supervised Time Series Representation Learning Joint-Embedding Predictive Architecture
Tsinghua Laboratory of Brain and Intelligence, Tsinghua University · School of Basic Medical Sciences, Tsinghua Medicine, Tsinghua University · School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University +2
Rethinking EEG-Based Disease Diagnosis: Decoupling Instance Representation Learning from Subject-Level Supervision
Jul 29, 2026Zhiyuan Ma, Zeyuan Li, Zhiyi Lu +7Electroencephalography Self-Supervised Time Series Representation Learning
School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University · Department of Biomedical Engineering, Southern University of Science and Technology
Neonatal Hypoxic-ischaemic Encephalopathy Classification from the EEG and HRV Signals Using a Conformer based Masked Autoencoder
Jul 26, 2026Shuwen Yu, William P Marnane, Geraldine B. Boylan +1Electroencephalography Masked Autoencoders
Department of Electrical & Electronic Engineering, School of Engineering and Architecture, University College Cork, Cork, Ireland · INFANT Research Centre, University College Cork, Cork, Ireland · Pediatrics and Child Health, University College Cork, Cork, Ireland
STS-NET: Spatio-Temporal Stress Network for Self-Supervised Crop Stress Detection using Satellite Image Time Series
Jul 21, 2026Pradeep Dalal, Rajiv Ranjan, Sushil Ghildiyal +2Agricultural Remote Sensing Self-Supervised Time Series Representation Learning
Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Rupnagar 140001, India · Department of Robotics and Autonomous Systems, Plaksha University, Mohali 140306, India
Joint-Embedding Predictive Architecture for Sensor-based Activity Recognition
Jul 17, 2026Mohd Halim Mohd Noor, Abdulrahman M. A. BarakaHuman Activity Recognition Self-Supervised Time Series Representation Learning
School of Computer Sciences, Universiti Sains Malaysia, 11800 Pulau Pinang, Malaysia · Artificial Intelligence Research Center, Ajman University, Ajman, United Arab Emirates · Al-Quds Open University, Ramallah, Palestine
DiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG Generic Representations
Jul 13, 2026Abdulkader Helwan, Lina Abou-Abbas, Hussein El Amouri +2Electroencephalography EEG Seizure Detection
Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon · Institute of Applied Artificial Intelligence, T´ELUQ University, Montreal, Canada
PhenoEmbed: Self-Supervised Multispectral UAV Time-Series Embeddings for Individual Tree Crown Phenology
Jul 11, 2026Taimur KhanPlant Phenotyping Self-Supervised Time Series Representation Learning
Helmholtz Centre for Environmental Research - UFZ, Community Ecology, Theodor-Lieser-Str. 4, 06120 Halle, Germany
FMMVCC: Fuzzy Mamba-based Multi-View Contrastive Clustering for Univariate Time Series
Jul 8, 2026Donato Cerciello, Leonardo Schiavo, Angel Panizo-LLedot +2Self-Supervised Time Series Representation Learning Clustering
Departamento de Sistemas Inform´aticos, Universidad Polit´ecnica de Madrid Madrid, Spain
STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning
Jul 7, 2026Roy Segal, Yoni Svechinsky, Tomer FeketeBrain Age Prediction Self-Supervised Time Series Representation Learning
Masked Generative-Contrastive Representation Learning for Cross-Dataset EEG-Based Emotion Recognition
Jul 5, 2026Huqin Weng, Jiayang Huang, Yimin Wen +3Contrastive Learning Self-Supervised Learning
MorphologyFM: A Foundation Model for Morphology-Aware Representation Learning from ECG and Pulse Oximetry Waveforms
Jul 3, 2026Saiyang Feng, Yuanyun Zhang, Shi LiRepresentation Learning Cross-Modal Representation Learning
University of the Chinese Academy of Sciences · Columbia University

Oct 5, 2026, cs.CVJ/K move · Enter open · S save

T-JEPA: A Temporal Joint-Embedding Predictive Architecture for Learning Better Remote Sensing Representations

Bowen Peng, Li Liu, Yongxiang Liu, Weijie Li+2

National University of Defense Technology, Changsha, China

Geospatial Representation Learning Self-Supervised Time Series Representation Learning Joint-Embedding Predictive Architecture

Open paper AskPDF arXiv

Earth observation (EO) data provide rich temporal supervision, yet existing remote sensing foundation models mainly exploit sequential observations through imposing predefined pairwise relations or aggregating holistic reconstruction context. We seek to further exploit the sparse and nonuniform temporal sampling inherent in EO sequences as supervisory signals. To this end, we propose T-JEPA, a temporal joint-embedding predictive architecture that learns time-gap-conditioned latent transitions. A shared single-frame encoder processes each observation, while a temporal predictor estimates the complete target latent field from a masked source latent representation and the actual elapsed time. Across multiple temporal intervals, these predictive constraints organize observed states into structured latent trajectories. Asymmetric metadata injection mitigates shortcut learning, and direct supervision across multiple temporal scales proves more effective than recursively rolling out intermediate states. In parallel, masked pixel reconstruction provides complementary supervision for preserving spatial details. Under matched pre-training data and throughput, T-JEPA achieves leading transfer performance on both static and temporal tasks. Analyses further reveal that T-JEPA learns representations with time-gap-dependent transition predictability and coherent latent dynamics, while maintaining strong cross-period consistency, representation diversity, and semantic discriminability.

Momentum

Related topics

Latest papers 91