VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion

2025/09/25 by Yanlong Wang, Hang Yu, Wang, Yanlong +17
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2510.03244

openalex publication_date 2025/09/25 · openalex created_date 2025/10/09 · openalex updated_date 2026/07/28

Abstract

Large time series foundation models often adopt channel-independent architectures to handle varying data dimensions, but this design ignores crucial cross-channel dependencies. Meanwhile, existing cross-modal methods predominantly rely on textual modalities, leaving the spatial pattern recognition capabilities of vision models underexplored for time series analysis. To address these limitations, we propose VFEM, a cross-modal forecasting model that leverages pre-trained large vision models (LVMs) to capture complex cross-variable patterns. VFEM transforms multivariate time series into visual representations, enabling LVMs to perceive spatial relationships that are not explicitly modeled by channel-independent models. Through a dual-branch architecture, visual and temporal features are independently extracted and then fused via cross-modal attention, allowing complementary information from both modalities to enhance forecasting. By freezing the LVM and training only 7.45% of the total parameters, VFEM achieves competitive performance on multiple benchmarks, offering a new perspective on multivariate time series forecasting.

Citations

• ms-Mamba: Multi-scale Mamba for Time-Series Forecasting
• There are no Champions in Supervised Long-Term Time Series Forecasting
• Sundial: A Family of Highly Capable Time Series Foundation Models
• Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
• VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters
• Are Language Models Actually Useful for Time Series Forecasting?
• UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting
• TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment
• Chronos: Learning the Language of Time Series
• MOMENT: A Family of Open Time-series Foundation Models
• Unified Training of Universal Time Series Forecasting Transformers
• Timer: Generative Pre-trained Transformers Are Large Time Series Models
• FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
• UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting
• iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
• TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
• Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
• TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
• A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
• FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Silhouettes: A graphical aid to the interpretation and validation of cluster analysis

Related

• Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting
• VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones
• From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?
• IMTS is Worth Time × Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
• MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysis