# Visual Time Series Forecasting: An Image-driven Approach

arXiv: https://arxiv.org/abs/2107.01273 · HTML: https://mlsanity.com/paper/2107.01273/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 39 references that are in the map.
- First posted on arXiv 2 Jul 2021.

## Builds on (most cited first, 12 of 12)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Generative Face Completion](https://mlsanity.com/paper/1704.05838/) (2017)
- [How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?](https://mlsanity.com/paper/1511.05101/) (2015)
- [Medical image denoising using convolutional denoising autoencoders](https://mlsanity.com/paper/1608.04667/) (2016)
- [Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections](https://mlsanity.com/paper/1606.08921/) (2016)
- [Forecasting with time series imaging](https://mlsanity.com/paper/1904.08064/) (2019)
- [Autowarp: Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders](https://mlsanity.com/paper/1810.10107/) (2018)
- [Trading via Image Classification](https://mlsanity.com/paper/1907.10046/) (2019)
- [Explaining Agent-Based Financial Market Simulation](https://mlsanity.com/paper/1909.11650/) (2019)
- [Clustering Time Series Data through Autoencoder-based Deep Learning Models](https://mlsanity.com/paper/2004.07296/) (2020)
- [The Effect of Visual Design in Image Classification](https://mlsanity.com/paper/1907.09567/) (2019)

## Abstract (arXiv)

In this work, we address time-series forecasting as a computer vision task. We capture input data as an image and train a model to produce the subsequent image. This approach results in predicting distributions as opposed to pointwise values. To assess the robustness and quality of our approach, we examine various datasets and multiple evaluation metrics. Our experiments show that our forecasting tool is effective for cyclic data but somewhat less for irregular data such as stock prices. Importantly, when using image-based evaluation metrics, we find our method to outperform various baselines, including ARIMA, and a numerical variation of our deep learning approach.