# Fast-AT: Fast Automatic Thumbnail Generation using Deep Neural Networks

arXiv: https://arxiv.org/abs/1612.04811 · HTML: https://mlsanity.com/paper/1612.04811/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2016.

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

- [Spatial-Semantic Collaborative Cropping for User Generated Content](https://mlsanity.com/paper/2401.08086/) (2024)
- [Human-centric Image Cropping with Partition-aware and Content-preserving Features](https://mlsanity.com/paper/2207.10269/) (2022)
- [A Hypothesis for the Aesthetic Appreciation in Neural Networks](https://mlsanity.com/paper/2108.02646/) (2021)
- [An Experience-based Direct Generation approach to Automatic Image Cropping](https://mlsanity.com/paper/2212.14561/) (2022)
- [Image Cropping under Design Constraints](https://mlsanity.com/paper/2310.08892/) (2023)
- [Subjective Portrait Region Cropping in Landscape Videos with Temporal Annotation Smoothing](https://mlsanity.com/paper/2604.24947/) (2026)

## Abstract (arXiv)

Fast-AT is an automatic thumbnail generation system based on deep neural networks. It is a fully-convolutional deep neural network, which learns specific filters for thumbnails of different sizes and aspect ratios. During inference, the appropriate filter is selected depending on the dimensions of the target thumbnail. Unlike most previous work, Fast-AT does not utilize saliency but addresses the problem directly. In addition, it eliminates the need to conduct region search on the saliency map. The model generalizes to thumbnails of different sizes including those with extreme aspect ratios and can generate thumbnails in real time. A data set of more than 70,000 thumbnail annotations was collected to train Fast-AT. We show competitive results in comparison to existing techniques.