# Discovering beautiful attributes for aesthetic image analysis

arXiv: https://arxiv.org/abs/1412.4940 · HTML: https://mlsanity.com/paper/1412.4940/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2014.

## Built on by (most cited first, 4 of 4)

- [Image Aesthetics Assessment Using Graph Attention Network](https://mlsanity.com/paper/2206.12869/) (2022)
- [A Survey on Image Aesthetic Assessment](https://mlsanity.com/paper/2103.11616/) (2021)
- [From Concepts to Judgments: Interpretable Image Aesthetic Assessment](https://mlsanity.com/paper/2603.18108/) (2026)
- [Aes3D: Aesthetic Assessment in 3D Gaussian Splatting](https://mlsanity.com/paper/2605.05155/) (2026)

## Abstract (arXiv)

Aesthetic image analysis is the study and assessment of the aesthetic properties of images. Current computational approaches to aesthetic image analysis either provide accurate or interpretable results. To obtain both accuracy and interpretability by humans, we advocate the use of learned and nameable visual attributes as mid-level features. For this purpose, we propose to discover and learn the visual appearance of attributes automatically, using a recently introduced database, called AVA, which contains more than 250,000 images together with their aesthetic scores and textual comments given by photography enthusiasts. We provide a detailed analysis of these annotations as well as the context in which they were given. We then describe how these three key components of AVA - images, scores, and comments - can be effectively leveraged to learn visual attributes. Lastly, we show that these learned attributes can be successfully used in three applications: aesthetic quality prediction, image tagging and retrieval.