Please use this identifier to cite or link to this item:
https://open.uns.ac.rs/handle/123456789/279
Title: | Increasing image memorability with neural style transfer | Authors: | Siarohin A. Zen G. Majtanović, Cveta Alameda-Pineda X. Ricci E. Sebe N. |
Issue Date: | 1-Jun-2019 | Journal: | ACM Transactions on Multimedia Computing, Communications and Applications | Abstract: | © 2019 Association for Computing Machinery. Recent works in computer vision and multimedia have shown that image memorability can be automatically inferred exploiting powerful deep-learning models. This article advances the state of the art in this area by addressing a novel and more challenging issue: "Given an arbitrary input image, can we make it more memorable? " To tackle this problem, we introduce an approach based on an editing-by-applying-filters paradigm: Given an input image, we propose to automatically retrieve a set of "style seeds," i.e., a set of style images that, applied to the input image through a neural style transfer algorithm, provide the highest increase in memorability. We show the effectiveness of the proposed approach with experiments on the publicly available LaMem dataset, performing both a quantitative evaluation and a user study. To demonstrate the flexibility of the proposed framework, we also analyze the impact of different implementation choices, such as using different state-of-the-art neural style transfer methods. Finally, we show several qualitative results to provide additional insights on the link between image style and memorability. | URI: | https://open.uns.ac.rs/handle/123456789/279 | ISSN: | 15516857 | DOI: | 10.1145/3311781 |
Appears in Collections: | Naučne i umetničke publikacije |
Show full item record
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.