Beauty Is in the Eye of the Beholder: Demographically Oriented Analysis of Aesthetics in Photographs

Citation

Yang, John See Su and Wong, Lai Kuan and Kairanbay, Magzhan (2019) Beauty Is in the Eye of the Beholder: Demographically Oriented Analysis of Aesthetics in Photographs. ACM Transactions on Multimedia Computing, Communications and Applications, 15 (2s). pp. 1-21. ISSN 1551-6857

[img] Text
254.pdf - Published Version
Restricted to Repository staff only

Download (9MB)

Abstract

Aesthetics is a subjective concept that is likely to be perceived differently among people of different ages, genders, and cultural backgrounds. While techniques that directly compute this concept in images has seen increasing attention by the multimedia and machine-learning community, there are very few attempts at encoding the influences from the photographer’s viewpoint. This work demonstrates how the aesthetic quality of photos can be better learned by accounting for the demographic background of a photographer. A new AVA-PD (Photographer Demographic) dataset is created to supplement the AVA dataset by providing photographers’ age, gender and location attributes. Two deep convolutional neural network (CNN) architectures are proposed to utilize demographic information for aesthetic prediction of photos; both are shown to yield better prediction capabilities compared to most existing approaches. By leveraging on AVA-PD meta-data, we also present some additional machine-learnable tasks such as identifying the photographer and predicting photography styles from a person’s gallery of photos.

Item Type: Article
Uncontrolled Keywords: Convolutional neural network
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Suzilawati Abu Samah
Date Deposited: 24 Feb 2022 03:18
Last Modified: 24 Feb 2022 03:18
URII: http://shdl.mmu.edu.my/id/eprint/9176

Downloads

Downloads per month over past year

View ItemEdit (login required)