mlsanityData to 7 Oct 2026

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

arXiv 2408.17253 ↗First posted 30 Aug 2024cs.CV cs.AI cs.LGcited by 87

Not on the map. Why?

Abstract (arXiv)

Foundation models have emerged as a promising approach in time series forecasting (TSF). Existing approaches either repurpose large language models (LLMs) or build large-scale time series datasets to develop TSF foundation models for universal forecasting. However, these methods face challenges due to the severe cross-domain gap or in-domain heterogeneity. This paper explores a new road to building a TSF foundation model from rich, high-quality natural images. Our key insight is that a visual masked autoencoder, pre-trained on the ImageNet dataset, can naturally be a numeric series forecaster. By reformulating TSF as an image reconstruction task, we bridge the gap between image pre-training and TSF downstream tasks. Surprisingly, without further adaptation in the time series domain, the proposed VisionTS could achieve better zero-shot forecast performance than existing TSF foundation models. With fine-tuning for one epoch, VisionTS could further improve the forecasting and achieve state-of-the-art performance in most cases. Extensive experiments reveal intrinsic similarities between images and real-world time series, suggesting that visual models may offer a "free lunch" for TSF and highlight the potential for future cross-modality research. Our code is publicly available at https://github.com/Keytoyze/VisionTS.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). Builds on 55 of its 81 references that are in the map. First posted on arXiv 30 Aug 2024.

Builds on

55 of 81 references.

References · 55

  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. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2022Scalable Diffusion Models with Transformerscited by 5,931
  8. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  9. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  10. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  11. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  12. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
38 more
  1. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  2. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  3. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
  4. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  5. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  6. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  7. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 730
  8. 2024Chronos: Learning the Language of Time Seriescited by 712
  9. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  10. 2023A decoder-only foundation model for time-series forecastingcited by 650
  11. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  12. 2024Unified Training of Universal Time Series Forecasting Transformerscited by 588
  13. 2023Large Language Models Are Zero-Shot Time Series Forecasterscited by 491
  14. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
  15. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 453
  16. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
  17. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 385
  18. 2021Monash Time Series Forecasting Archivecited by 256
  19. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 242
  20. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 198
  21. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 170
  22. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 163
  23. 2022ETSformer: Exponential Smoothing Transformers for Time-series Forecastingcited by 146
  24. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 143
  25. 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Seriescited by 120
  26. 2024CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuningcited by 105
  27. 2024SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameterscited by 103
  28. 2023The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecastingcited by 100
  29. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  30. 2015Imaging Time-Series to Improve Classification and Imputationcited by 85
  31. 2023Time Series as Images: Vision Transformer for Irregularly Sampled Time Seriescited by 79
  32. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  33. 2017Classification of Time-Series Images Using Deep Convolutional Neural Networkscited by 38
  34. 2024Multi-Patch Prediction: Adapting LLMs for Time Series Representation Learningcited by 25
  35. 2023Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shiftcited by 23
  36. 2019Forecasting with time series imagingcited by 22
  37. 2023Leveraging Vision-Language Models for Granular Market Change Predictioncited by 22
  38. 2024TimeSiam: A Pre-Training Framework for Siamese Time-Series Modelingcited by 20

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 47; 2026: 37.

87 papers.

Sort:

By area:

  1. 2024GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluationcited by 188
  2. 2024CBraMod: A Criss-Cross Brain Foundation Model for EEG Decodingcited by 188
  3. 2024ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoningcited by 95
  4. 2025Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecastingcited by 59
  5. 2025This Time is Different: An Observability Perspective on Time Series Foundation Modelscited by 57
  6. 2025TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loopcited by 39
  7. 2025TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecastercited by 36
  8. 2025Representation Learning for Tabular Data: A Comprehensive Surveycited by 36
  9. 2025Aurora: Towards Universal Generative Multimodal Time Series Forecastingcited by 28
  10. 2025Harnessing Vision Models for Time Series Analysis: A Surveycited by 26
  11. 2025Mantis: Lightweight Foundation Model for Time Series Classificationcited by 21
  12. 2025Output Scaling: YingLong-Delayed Chain of Thought in a Large Pretrained Time Series Forecasting Modelcited by 21
38 more
  1. 2025T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Modelscited by 19
  2. 2026AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discoverycited by 17
  3. 2025BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Modelscited by 16
  4. 2025Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Modelscited by 15
  5. 2025Lightweight Online Adaption for Time Series Foundation Model Forecastscited by 14
  6. 2025CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Datacited by 12
  7. 2025Can Multimodal LLMs Perform Time Series Anomaly Detection?cited by 11
  8. 2025VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbonescited by 11
  9. 2025TimeHF: Billion-Scale Time Series Models Guided by Human Feedbackcited by 10
  10. 2025Performance of Zero-Shot Time Series Foundation Models on Cloud Datacited by 10
  11. 2025TimesBERT: A BERT-Style Foundation Model for Time Series Understandingcited by 10
  12. 2025TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoningcited by 10
  13. 2025Rethinking Evaluation in the Era of Time Series Foundation Models: (Un)known Information Leakage Challengescited by 10
  14. 2026Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Modelscited by 10
  15. 2026MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategiescited by 10
  16. 2025Vision-Enhanced Time Series Forecasting via Latent Diffusion Modelscited by 9
  17. 2025Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecastingcited by 8
  18. 2025Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Modelscited by 8
  19. 2025From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?cited by 7
  20. 2025CaTS-Bench: Can Language Models Describe Time Series?cited by 7
  21. 2025Xihe: Scalable Zero-Shot Time Series Learner Via Hierarchical Interleaved Block Attentioncited by 7
  22. 2025Unlocking Pretrained Vision Transformers for Time Series Classificationcited by 6
  23. 2025AimTS: Augmented Series and Image Contrastive Learning for Time Series Classificationcited by 5
  24. 2025VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysiscited by 5
  25. 2026Learning the Context of Errors: Black-Box Online Adaptation of Time Series Foundation Modelscited by 5
  26. 2025LAST SToP For Modeling Asynchronous Time Seriescited by 4
  27. 2025Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecastingcited by 4
  28. 2025MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysiscited by 4
  29. 2026TimeOmni-VL: Unified Models for Time Series Understanding and Generationcited by 4
  30. 2026TempusBench: An Evaluation Framework for Time-Series Forecastingcited by 4
  31. 2025SeisMoLLM: Advancing Seismic Monitoring via Cross-modal Transfer with Pre-trained Large Language Modelcited by 3
  32. 2025One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoocited by 3
  33. 2025FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecastingcited by 3
  34. 2026Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoningcited by 3
  35. 2026TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuningcited by 3
  36. 2026TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Modelscited by 3
  37. 2025IMTS is Worth Time × Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Predictioncited by 2
  38. 2025Towards Measuring and Modeling Geometric Structures in Time Series Forecasting via Image Modalitycited by 2

50 most cited of 87 All 87 (JSON)