English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In the fields of Experimental and Computational Aesthetics, numerous imagedatasets have been created over the last two decades. In the present work, weprovide a comparative overview of twelve image datasets that include aestheticratings (beauty, liking or aesthetic quality) and investigate thereproducibility of results across different datasets. Specifically, we examinehow consistently the ratings can be predicted by using either (A) a set of 20previously studied statistical image properties, or (B) the layers of aconvolutional neural network developed for object recognition. Our findingsreveal substantial variation in the predictability of aesthetic ratings acrossthe different datasets. However, consistent similarities were found fordatasets containing either photographs or paintings, suggesting differentrelevant features in the aesthetic evaluation of these two image genres. To oursurprise, statistical image properties and the convolutional neural networkpredict aesthetic ratings with similar accuracy, highlighting a significantoverlap in the image information captured by the two methods. Nevertheless, thediscrepancies between the datasets call into question the generalizability ofprevious research findings on single datasets. Our study underscores theimportance of considering multiple datasets to improve the validity andgeneralizability of research results in the fields of experimental andcomputational aesthetics.

Predicting beauty, liking, and aesthetic quality: A comparative analysis of image databases for visual aesthetics research