paper-with-me

홈 › Papers

TriTS: Time Series Forecasting from a Multimodal Perspective

2026-04-17 · Xiang Ao arxiv

Time series forecasting plays a pivotal role in critical sectors such as finance, energy, transportation, and meteorology. However, Long-term Time Series Forecasting (LTSF) remains a significant challenge because real-world signals contain highly entangled temporal dynamics that are difficult to fully capture from a purely 1D perspective. To break this representation bottleneck, we propose TriTS, a novel cross-modal disentanglement framework that projects 1D time series into orthogonal time, frequency, and 2D-vision spaces.To seamlessly bridge the 1D-to-2D modality gap without the prohibitive $O(N^2)$ computational overhead of Vision Transformers (ViTs), we introduce a Period-Aware Reshaping strategy and incorporate Visual Mamba (Vim). This approach efficiently models cross-period dependencies as global visual textures while maintaining linear computational complexity. Complementing this, we design a Multi-Resolution Wavelet Mixing (MR-WM) module for the frequency modality, which explicitly decouples non-stationary signals into trend and noise components to achieve fine-grained time-frequency localization. Finally, a streaming linear branch is retained in the time domain to anchor numerical stability. By dynamically fusing these three complementary representations, TriTS effectively adapts to diverse data contexts. Extensive experiments across multiple benchmark datasets demonstrate that TriTS achieves state-of-the-art (SOTA) performance, fundamentally outperforming existing vision-based forecasters by drastically reducing both parameter count and inference latency.

📄 PDF Abstract BibTeX arXiv:2604.16748

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series Forecasting

Similar Papers 제목 키워드 기반

Adaptive Information Routing for Multimodal Time Series Forecasting

2025-12-11 · Jun Seo, Hyeokjun Choe, Seohui Bae, Soyeon Park 외 arxiv

Time series forecasting is a critical task for artificial intelligence with numerous real-world applications. Traditional approaches primarily rely on historical time series data to predict the future values. However, in…

Time Series Forecasting

MoTime: A Dataset Suite for Multimodal Time Series Forecasting

2025-05-21 · Xin Zhou, Weiqing Wang, Francisco J. Baldán, Wray Buntine 외

While multimodal data sources are increasingly available from real-world forecasting, most existing research remains on unimodal time series. In this work, we present MoTime, a suite of multimodal time series forecasting…

Time SeriesTime Series Forecasting

Unveiling the Potential of Text in High-Dimensional Time Series Forecasting

2025-01-13 · Xin Zhou, Weiqing Wang, Shilin Qu, Zhiqiang Zhang 외

Time series forecasting has traditionally focused on univariate and multivariate numerical data, often overlooking the benefits of incorporating multimodal information, particularly textual data. In this paper, we propos…

Time SeriesTime Series Forecasting

Empowering Time Series Analysis with Large-Scale Multimodal Pretraining

2026-02-05 · Peng Chen, Siyuan Wang, Shiyan Hu, Xingjian Wu 외 arxiv

While existing time series foundation models primarily rely on large-scale unimodal pretraining, they lack complementary modalities to enhance time series understanding. Building multimodal foundation models is a natural…

Time Series ForecastingTime Series AnalysisAnomaly Detection

TiMi: Empower Time Series Transformers with Multimodal Mixture of Experts

2026-02-25 · Jiafeng Lin, Yuxuan Wang, Huakun Luo, Zhongyi Pei 외 arxiv

Multimodal time series forecasting has garnered significant attention for its potential to provide more accurate predictions than traditional single-modality models by leveraging rich information inherent in other modali…

Time Series Forecasting