From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecasting

arXiv:2403.11047v1 Announce Type: new
Abstract: Time series forecasting plays a crucial role in decision-making across various domains, but it presents significant challenges. Recent studies have explored image-driven approaches using computer vision models to address these challenges, often employing lineplots as the visual representation of time series data. In this paper, we propose a novel approach that uses time-frequency spectrograms as the visual representation of time series data. We introduce the use of a vision transformer for multimodal learning, showcasing the …

abstract arxiv challenges computer computer vision cs.ai cs.ce cs.cv data decision domains forecasting image making pixels predictions representation role series spectrogram studies time series time series forecasting transformer type vision vision models visual