mlsanityData to 14 Oct 2026

IMTS is Worth Time × Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction

arXiv 2505.22815 ↗First posted 28 May 2025cs.CV cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Irregular Multivariate Time Series (IMTS) forecasting is challenging due to the unaligned nature of multi-channel signals and the prevalence of extensive missing data. Existing methods struggle to capture reliable temporal patterns from such data due to significant missing values. While pre-trained foundation models show potential for addressing these challenges, they are typically designed for Regularly Sampled Time Series (RTS). Motivated by the visual Mask AutoEncoder's (MAE) powerful capability for modeling sparse multi-channel information and its success in RTS forecasting, we propose VIMTS, a framework adapting Visual MAE for IMTS forecasting. To mitigate the effect of missing values, VIMTS first processes IMTS along the timeline into feature patches at equal intervals. These patches are then complemented using learned cross-channel dependencies. Then it leverages visual MAE's capability in handling sparse multichannel data for patch reconstruction, followed by a coarse-to-fine technique to generate precise predictions from focused contexts. In addition, we integrate self-supervised learning for improved IMTS modeling by adapting the visual MAE to IMTS data. Extensive experiments demonstrate VIMTS's superior performance and few-shot capability, advancing the application of visual foundation models in more general time series tasks. Our code is available at https://github.com/WHU-HZY/VIMTS.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 44 of its 71 references that are in the map. First posted on arXiv 28 May 2025.

Builds on

44 of 71 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2022Generative Adversarial Networkscited by 5,627
  8. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  9. 2018Neural Ordinary Differential Equationscited by 3,779
  10. 2023A Survey of Large Language Modelscited by 2,576
  11. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  12. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
32 more
  1. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  2. 2023A decoder-only foundation model for time-series forecastingcited by 692
  3. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  4. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 614
  5. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  6. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  7. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
  8. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  9. 2020Time Series Forecasting With Deep Learning: A Surveycited by 459
  10. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
  11. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  12. 2024Foundation Models for Time Series Analysis: A Tutorial and Surveycited by 239
  13. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 238
  14. 2019GRU-ODE-Bayes: Continuous modeling of sporadically-observed time seriescited by 231
  15. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 168
  16. 2019Set Functions for Time Seriescited by 138
  17. 2023FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspectivecited by 127
  18. 2021Graph-Guided Network for Irregularly Sampled Multivariate Time Seriescited by 111
  19. 2021Modeling Irregular Time Series with Continuous Recurrent Unitscited by 103
  20. 2021Neural Flows: Efficient Alternative to Neural ODEscited by 101
  21. 2016Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequencescited by 99
  22. 2024VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasterscited by 88
  23. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  24. 2016Modeling Missing Data in Clinical Time Series with RNNscited by 80
  25. 2023Time Series as Images: Vision Transformer for Irregularly Sampled Time Seriescited by 79
  26. 2024Deep Learning for Multivariate Time Series Imputation: A Surveycited by 57
  27. 2023Warpformer: A Multi-scale Modeling Approach for Irregular Clinical Time Seriescited by 55
  28. 2020A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Seriescited by 42
  29. 2020Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filteringcited by 34
  30. 2023Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networkcited by 20
  31. 2024ViTime: Foundation Model for Time Series Forecasting Powered by Vision Intelligencecited by 11
  32. 2024Representation Learning for Wearable-Based Applications in the Case of Missing Datacited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Hierarchical ODE: Learning Continuous-Time Physical Prototypes for Early Link Failure Detectioncited by 0
  2. 2026MissHyper: Restoring Clinical Synchronicity in Missingness-Guided Hypergraph Forecastingcited by 0