# Learning Visual Importance for Graphic Designs and Data Visualizations

arXiv: https://arxiv.org/abs/1708.02660 · HTML: https://mlsanity.com/paper/1708.02660/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2017.

## Built on by (most cited first, 22 of 22)

- [Constrained Graphic Layout Generation via Latent Optimization](https://mlsanity.com/paper/2108.00871/) (2021)
- [Generative AI for Visualization: State of the Art and Future Directions](https://mlsanity.com/paper/2404.18144/) (2024)
- [Deep Saliency Prior for Reducing Visual Distraction](https://mlsanity.com/paper/2109.01980/) (2021)
- [Understanding Visual Saliency in Mobile User Interfaces](https://mlsanity.com/paper/2101.09176/) (2021)
- [Predicting and Explaining Mobile UI Tappability with Vision Modeling and Saliency Analysis](https://mlsanity.com/paper/2204.02448/) (2022)
- [Trends, Applications, and Challenges in Human Attention Modelling](https://mlsanity.com/paper/2402.18673/) (2024)
- [UniAR: A Unified model for predicting human Attention and Responses on visual content](https://mlsanity.com/paper/2312.10175/) (2023)
- [Scanpath Prediction on Information Visualisations](https://mlsanity.com/paper/2112.02340/) (2021)
- [Text2Poster: Laying out Stylized Texts on Retrieved Images](https://mlsanity.com/paper/2301.02363/) (2023)
- [What Do Deep Saliency Models Learn about Visual Attention?](https://mlsanity.com/paper/2310.09679/) (2023)
- [Learning Personal Style from Few Examples](https://mlsanity.com/paper/2105.14457/) (2021)
- [Predicting Visual Attention in Graphic Design Documents](https://mlsanity.com/paper/2407.02439/) (2024)
- [Reinforced Labels: Multi-Agent Deep Reinforcement Learning for Point-Feature Label Placement](https://mlsanity.com/paper/2303.01388/) (2023)
- [From Fragment to One Piece: A Survey on AI-Driven Graphic Design](https://mlsanity.com/paper/2503.18641/) (2025)
- [VizAI : Selecting Accurate Visualizations of Numerical Data](https://mlsanity.com/paper/2111.04190/) (2021)
- [Reimagining Application User Interface (UI) Design using Deep Learning Methods: Challenges and Opportunities](https://mlsanity.com/paper/2303.13055/) (2023)
- [Tell Me Without Telling Me: Two-Way Prediction of Visualization Literacy and Visual Attention](https://mlsanity.com/paper/2508.03713/) (2025)
- [From Answer Givers to Design Mentors: Guiding LLMs with the Cognitive Apprenticeship Model](https://mlsanity.com/paper/2601.19053/) (2026)
- [Learning Aesthetic Layouts via Visual Guidance](https://mlsanity.com/paper/2107.06262/) (2021)
- [Evaluation Metrics for Automated Typographic Poster Generation](https://mlsanity.com/paper/2402.06945/) (2024)
- [GRAPHIC--Guidelines for Reviewing Algorithmic Practices in Human-centred Design and Interaction for Creativity](https://mlsanity.com/paper/2511.17443/) (2025)
- [TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design](https://mlsanity.com/paper/2605.20731/) (2026)

## Abstract (arXiv)

Knowing where people look and click on visual designs can provide clues about how the designs are perceived, and where the most important or relevant content lies. The most important content of a visual design can be used for effective summarization or to facilitate retrieval from a database. We present automated models that predict the relative importance of different elements in data visualizations and graphic designs. Our models are neural networks trained on human clicks and importance annotations on hundreds of designs. We collected a new dataset of crowdsourced importance, and analyzed the predictions of our models with respect to ground truth importance and human eye movements. We demonstrate how such predictions of importance can be used for automatic design retargeting and thumbnailing. User studies with hundreds of MTurk participants validate that, with limited post-processing, our importance-driven applications are on par with, or outperform, current state-of-the-art methods, including natural image saliency. We also provide a demonstration of how our importance predictions can be built into interactive design tools to offer immediate feedback during the design process.