mlsanityData to 14 Oct 2026

Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting

arXiv 2505.24003 ↗First posted 29 May 2025cs.LG cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Time series, typically represented as numerical sequences, can also be transformed into images and texts, offering multi-modal views (MMVs) of the same underlying signal. These MMVs can reveal complementary patterns and enable the use of powerful pre-trained large models, such as large vision models (LVMs), for long-term time series forecasting (LTSF). However, as we identified in this work, the state-of-the-art (SOTA) LVM-based forecaster poses an inductive bias towards "forecasting periods". To harness this bias, we propose DMMV, a novel decomposition-based multi-modal view framework that leverages trend-seasonal decomposition and a novel backcast-residual based adaptive decomposition to integrate MMVs for LTSF. Comparative evaluations against 14 SOTA models across diverse datasets show that DMMV outperforms single-view and existing multi-modal baselines, achieving the best mean squared error (MSE) on 6 out of 8 benchmark datasets. The code for this paper is available at: https://github.com/D2I-Group/dmmv.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 49 of its 56 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

49 of 56 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  9. 2014Going Deeper with Convolutionscited by 4,241
  10. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  11. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  12. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
37 more
  1. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  2. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  3. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  4. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  5. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  6. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  7. 2019N-BEATS: Neural basis expansion analysis for interpretable time series forecastingcited by 753
  8. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  9. 2021AST: Audio Spectrogram Transformercited by 643
  10. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  11. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 500
  12. 2022Transformers in Time Series: A Surveycited by 497
  13. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 391
  14. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  15. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 172
  16. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 168
  17. 2016On Deep Multi-View Representation Learning: Objectives and Optimizationcited by 162
  18. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 148
  19. 2024Large Language Models for Time Series: A Surveycited by 114
  20. 2024CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuningcited by 108
  21. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 107
  22. 2024CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patternscited by 106
  23. 2024VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasterscited by 88
  24. 2023Time Series as Images: Vision Transformer for Irregularly Sampled Time Seriescited by 79
  25. 2021Time Series Prediction using Deep Learning Methods in Healthcarecited by 74
  26. 2017Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Predictioncited by 67
  27. 2025Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecastingcited by 63
  28. 2024Empowering Time Series Analysis with Large Language Models: A Surveycited by 60
  29. 2024Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modelingcited by 44
  30. 2022DEPTS: Deep Expansion Learning for Periodic Time Series Forecastingcited by 29
  31. 2025Harnessing Vision Models for Time Series Analysis: A Surveycited by 26
  32. 2019Forecasting with time series imagingcited by 22
  33. 2023Leveraging Vision-Language Models for Granular Market Change Predictioncited by 22
  34. 2024See it, Think it, Sorted: Large Multimodal Models are Few-shot Time Series Anomaly Analyzerscited by 20
  35. 2024Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecastingcited by 18
  36. 2024From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecastingcited by 9
  37. 2024On the Feasibility of Vision-Language Models for Time-Series Classificationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 7.

9 papers.

  1. 2025VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbonescited by 12
  2. 2025UniCast: A Unified Framework for Instance-Conditioned Multimodal Time-Series Forecastingcited by 2
  3. 2026Visual Reasoning over Time Series via Multi-Agent Systemcited by 2
  4. 2026Multi-Modal Time Series Prediction via Mixture of Modulated Expertscited by 1
  5. 2026SSDA: Bridging Spectral and Structural Gaps via Dual Adaptation for Vision-Based Time Series Forecastingcited by 1
  6. 2026Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoningcited by 0
  7. 2026In-Context Inpainting for Time Series Forecastingcited by 0
  8. 2026MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecastingcited by 0
  9. 2026KALEIDO: Input-Space Adaptation of a Vision Model for Time-Series Forecasting Through Gated Fold Geometriescited by 0