Harnessing Vision Models for Time Series Analysis: A Survey
nijingchao
Abstract
Time series analysis has witnessed the inspiring development from traditional autoregressive models, deep learning models, to recent Transformers and Large Language Models (LLMs). Efforts in leveraging vision models for time series analysis have also been made along the way but are less visible to the community due to the predominant research on sequence modeling in this domain. However, the discrepancy between continuous time series and the discrete token space of LLMs, and the challenges in explicitly modeling the correlations of variates in multivariate time series have shifted some research attentions to the equally successful Large Vision Models (LVMs) and Vision Language Models (VLMs). To fill the blank in the existing literature, this survey discusses the advantages of vision models over LLMs in time series analysis. It provides a comprehensive and in-depth overview of the existing methods, with dual views of detailed taxonomy that answer the key research questions including how to encode time series as images and how to model the imaged time series for various tasks. Additionally, we address the challenges in the pre- and post-processing steps involved in this framework and outline future directions to further advance time series analysis with vision models.
Community
New Survey: Harnessing Vision Models for Time Series Analysis: A Survey
Preprint: https://www.arxiv.org/abs/2502.08869
Github: https://github.com/D2I-Group/awesome-vision-time-series
This survey presents a comprehensive review of using vision models for time series analysis, highlighting their advantages over Transformers and Large Language Models (LLMs). While sequence modeling has been the predominant approach, this survey explores how Large Vision Models (LVMs) and Vision Language Models (VLMs) can better handle time series data.
Key Features
- A comprehensive and in-depth overview of the existing methods
- Taxonomy view I: time series to image transformation
- The methods include Line Plot, Heatmap, Spectrogram, Gramian Angular Field (GAF), Recurrence Plot (RP), Markov Transition Field (MTF), etc.
- Taxonomy view II: imaged time series modeling
- The survey includes conventional vision models, Large Vision Models (LVMs), Large Multimodal Models (LMMs), and designs of task-specific heads.
- A review of the challenges and solutions in the pre- and post-processing steps involved in this framework
- Discussions on future directions to further advance time series analysis with vision models
- Code for imaging time series with the methods discussed in the survey
We hope this survey could serve as a complement to the existing surveys on Transformer, LLMs and foundation models for time series, and provide a complete view on the process of using vision models for time series analysis, so as to be an insightful reference to the developers in this area.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting (2025)
- Investigating Compositional Reasoning in Time Series Foundation Models (2025)
- On the Feasibility of Vision-Language Models for Time-Series Classification (2024)
- TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agents (2025)
- Using Pre-trained LLMs for Multivariate Time Series Forecasting (2025)
- Large Language Models are Few-shot Multivariate Time Series Classifiers (2025)
- Position: Empowering Time Series Reasoning with Multimodal LLMs (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper