Fast-AT: Fast Automatic Thumbnail Generation using Deep Neural Networks
This addresses the problem of efficient and scalable thumbnail creation for users in media and web applications, though it is incremental as it builds on existing deep learning approaches.
The paper tackles automatic thumbnail generation by proposing Fast-AT, a fully-convolutional deep neural network that learns filters for different thumbnail sizes and aspect ratios, eliminating the need for saliency-based methods and enabling real-time generation with competitive results.
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.