Naslov
How Convolutional Neural Networks Remember Art

Autori
Cetinić, Eva ; Lipić, Tomislav ; Grgić, Sonja

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the International Conference on Systems, Signals and Image Processing - IWSSIP 2018 / Planinšič, Peter ; Gleich, Dušan - Piscataway (NJ) : Institute of Electrical and Electronics Engineers (IEEE), 2018

ISBN
978-1-5386-6979-2

Skup
25th International Conference on Systems, Signals and Image Processing (IWSSIP 2018)

Mjesto i datum
Maribor, Slovenija, 20.06.2018. - 22.06.2018

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Image Memorability ; Fine Art ; Convolutional Neural Networks

Sažetak
Inspired by the successful performance of Convolutional Neural Networks (CNN) in automatically predicting complex image properties such as memorability, in this work we explore their transferability to the domain of art images. We employ a CNN model trained to predict memorability scores of natural images to explore the memorability of artworks belonging to different genres and styles. Our experiments show that nude painting and portrait are the most memorable genres, while landscape and marine painting are the least memorable. Regarding image style, we show that abstract styles tend to be more memorable than figurative. Additionally, on the subset of abstract images, we explore the relation between memorability and other features related to composition and color, as well as the sentiment evoked by the image. We show that there is no correlation between symmetry and memorability, however memorability positively correlates with the image’s probability of evoking positive sentiment.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA