paper-with-me

홈 › Papers

STaT: Resolving Shape Distortion in Non-Stationary Time Series via Tri-Modal Synergy

2026-05-25 · Hui Cheng, Jinsheng Guo, Zhenhao Weng, Yan Qiao, Meng Li arxiv

Recent research in time series forecasting frequently investigates the integration of textual and visual modalities with numerical models to better navigate non-stationary environments. Despite delivering solid numerical results, existing multi-modal approaches usually encounter a dilemma: prioritizing the minimization of average errors can result in excessively smooth forecasts that overlook essential fluctuations. To resolve this limitation, we introduce STaT, an innovative multimodal architecture for Symbolic-Temporal-Textual Alignment, which seamlessly unites three synergistic modalities. Specifically, the symbolic modality converts continuous time series into discrete tokens, facilitating the accurate identification of structural patterns and turning points; the temporal modality extracts inherent sequential dependencies; and the textual modality leverages domain semantics to steer the macroscopic forecasting trends. Comprehensive evaluations on eight real-world benchmarks indicate that STaT delivers exceptional performance, enhancing conventional magnitude indicators by up to 8.9% while simultaneously decreasing shape distortion by up to 8.5%.

📄 PDF Abstract BibTeX arXiv:2605.25943

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series Forecasting

Similar Papers 제목 키워드 기반

Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models

2019-09-19 · NeurIPS 2019 12 · Vincent Le Guen, Nicolas Thome

This paper addresses the problem of time series forecasting for non-stationary signals and multiple future steps prediction. To handle this challenging task, we introduce DILATE (DIstortion Loss including shApe and TimE)…

Change DetectionDynamic Time WarpingTime SeriesTime Series Analysis+2

Deep Time Series Forecasting with Shape and Temporal Criteria

2021-04-09 · Vincent Le Guen, Nicolas Thome

This paper addresses the problem of multi-step time series forecasting for non-stationary signals that can present sudden changes. Current state-of-the-art deep learning forecasting methods, often trained with variants o…

Change DetectionDiversityDynamic Time WarpingTime Series+2

Tracking Changing Stimuli in Continuous Attractor Neural Networks

2008-12-01 · NeurIPS 2008 12 · K. Wong, Si Wu, Chi Fung

Continuous attractor neural networks (CANNs) are emerging as promising models for describing the encoding of continuous stimuli in neural systems. Due to the translational invariance of their neuronal interactions, CANNs…

Partial Sum Processes of Residual-Based and Wald-type Break-Point Statistics in Time Series Regression Models

2022-01-31 · Christis Katsouris

We revisit classical asymptotics when testing for a structural break in linear regression models by obtaining the limit theory of residual-based and Wald-type processes. First, we establish the Brownian bridge limiting d…

regressionTime SeriesTime Series AnalysisTime Series Regression

SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Images

2018-11-20 · Yeonkun Lee, Jaeseok Jeong, Jongseob Yun, Wonjune Cho 외

Omni-directional cameras have many advantages overconventional cameras in that they have a much wider field-of-view (FOV). Accordingly, several approaches have beenproposed recently to apply convolutional neural networks…

Semantic Segmentation