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

2025/05/29 by ChengAo Shen, Wenchao Yu, Shen, ChengAo +11 · 3 citations
Engineering · #Advanced Image Fusion Techniques #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Infrared Target Detection Methodologies #Machine Learning (cs.LG) #Remote-Sensing Image Classification

paper · pdf · doi:10.48550/arxiv.2505.24003

openalex publication_date 2025/05/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Toward Reasoning-Centric Time-Series Analysis
• UniCast: A Unified Framework for Instance-Conditioned Multimodal Time-Series Forecasting
• VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones

Related

• From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?
• VFEM: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion
• VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones
• OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting
• A Multi-scale Representation Learning Framework for Long-Term Time Series Forecasting