Fast-At: Fast Automatic Thumbnail Generation Using Deep Neural Networks

Seyed A. Esmaeili, Bharat Singh, Larry S. Davis; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4622-4630

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 over 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.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Esmaeili_2017_CVPR,
author = {Esmaeili, Seyed A. and Singh, Bharat and Davis, Larry S.},
title = {Fast-At: Fast Automatic Thumbnail Generation Using Deep Neural Networks},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}