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

TL;DR

Fast-AT is a real-time, fully-convolutional neural network system for automatic thumbnail generation that directly learns to produce thumbnails of various sizes and aspect ratios without relying on saliency detection.

Contribution

It introduces a novel deep neural network approach that directly generates thumbnails, eliminating the need for saliency maps and region search, and handles diverse thumbnail sizes efficiently.

Findings

Achieves real-time thumbnail generation.

Demonstrates competitive performance against existing methods.

Successfully generalizes to extreme aspect ratios.

Abstract

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.