# Multimodal Quasi-AutoRegression: Forecasting the visual popularity of new fashion products

arXiv: https://arxiv.org/abs/2204.04014 · HTML: https://mlsanity.com/paper/2204.04014/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 8 Apr 2022.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Generating Sequences With Recurrent Neural Networks](https://mlsanity.com/paper/1308.0850/) (2013)
- [Time Series Forecasting With Deep Learning: A Survey](https://mlsanity.com/paper/2004.13408/) (2020)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [Fashion Meets Computer Vision: A Survey](https://mlsanity.com/paper/2003.13988/) (2020)
- [Fashion Forward: Forecasting Visual Style in Fashion](https://mlsanity.com/paper/1705.06394/) (2017)
- [A Memory-Network Based Solution for Multivariate Time-Series Forecasting](https://mlsanity.com/paper/1809.02105/) (2018)
- [GeoStyle: Discovering Fashion Trends and Events](https://mlsanity.com/paper/1908.11412/) (2019)
- [Knowledge Enhanced Neural Fashion Trend Forecasting](https://mlsanity.com/paper/2005.03297/) (2020)
- [Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends](https://mlsanity.com/paper/2109.09824/) (2021)
- [From Paris to Berlin: Discovering Fashion Style Influences Around the World](https://mlsanity.com/paper/2004.01316/) (2020)
- [LAVARNET: Neural Network Modeling of Causal Variable Relationships for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2009.00945/) (2020)

## Built on by (most cited first, 6 of 6)

- [MoTime: A Dataset Suite for Multimodal Time Series Forecasting](https://mlsanity.com/paper/2505.15072/) (2025)
- [Sample Selection via Contrastive Fragmentation for Noisy Label Regression](https://mlsanity.com/paper/2502.17771/) (2025)
- [VICTOR: Visual Incompatibility Detection with Transformers and Fashion-specific contrastive pre-training](https://mlsanity.com/paper/2207.13458/) (2022)
- [Integrating Domain Knowledge into Large Language Models for Enhanced Fashion Recommendations](https://mlsanity.com/paper/2502.15696/) (2025)
- [On the use of learning-based forecasting methods for ameliorating fashion business processes: A position paper](https://mlsanity.com/paper/2211.04798/) (2022)
- [Design-time Fashion Popularity Forecasting in VR Environments](https://mlsanity.com/paper/2212.07187/) (2022)

## Abstract (arXiv)

Estimating the preferences of consumers is of utmost importance for the fashion industry as appropriately leveraging this information can be beneficial in terms of profit. Trend detection in fashion is a challenging task due to the fast pace of change in the fashion industry. Moreover, forecasting the visual popularity of new garment designs is even more demanding due to lack of historical data. To this end, we propose MuQAR, a Multimodal Quasi-AutoRegressive deep learning architecture that combines two modules: (1) a multi-modal multi-layer perceptron processing categorical, visual and textual features of the product and (2) a quasi-autoregressive neural network modelling the "target" time series of the product's attributes along with the "exogenous" time series of all other attributes. We utilize computer vision, image classification and image captioning, for automatically extracting visual features and textual descriptions from the images of new products. Product design in fashion is initially expressed visually and these features represent the products' unique characteristics without interfering with the creative process of its designers by requiring additional inputs (e.g manually written texts). We employ the product's target attributes time series as a proxy of temporal popularity patterns, mitigating the lack of historical data, while exogenous time series help capture trends among interrelated attributes. We perform an extensive ablation analysis on two large scale image fashion datasets, Mallzee and SHIFT15m to assess the adequacy of MuQAR and also use the Amazon Reviews: Home and Kitchen dataset to assess generalisability to other domains. A comparative study on the VISUELLE dataset, shows that MuQAR is capable of competing and surpassing the domain's current state of the art by 4.65% and 4.8% in terms of WAPE and MAE respectively.