Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Hierarchical layout-aware graph convolutional network for unified aesthetics assessment

Dongyu, She, Lai, Yukun ORCID: https://orcid.org/0000-0002-2094-5680, Gaoxiong, Yi and Kun, Xu 2021. Hierarchical layout-aware graph convolutional network for unified aesthetics assessment. Presented at: IEEE/CVF Conference on Computer Vision and Pattern Recognition, Virtual/10.1109/CVPR46437.2021.00837, 20-25 June 2021. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 10.1109/CVPR46437.2021.00837

[thumbnail of AestheticsAssessment_CVPR2021.pdf]
Preview
PDF - Accepted Post-Print Version
Download (3MB) | Preview

Abstract

Learning computational models of image aesthetics can have a substantial impact on visual art and graphic design. Although automatic image aesthetics assessment is a challenging topic by its subjective nature, psychological studies have confirmed a strong correlation between image layouts and perceived image quality. While previous state-of-the-art methods attempt to learn holistic information using deep Convolutional Neural Networks (CNNs), our approach is motivated by the fact that Graph Convolutional Network (GCN) architecture is conceivably more suited for modeling complex relations among image regions than vanilla convolutional layers. Specifically, we present a Hierarchical Layout-Aware Graph Convolutional Network (HLA-GCN) to capture layout information. It is a dedicated double-subnet neural network consisting of two LA-GCN modules. The first LA-GCN module constructs an aesthetics-related graph in the coordinate space and performs reasoning over spatial nodes. The second LA-GCN module performs graph reasoning after aggregating significant regions in a latent space. The model output is a hierarchical representation with layout-aware features from both spatial and aggregated nodes for unified aesthetics assessment. Extensive evaluations show that our proposed model outperforms the state-of-the-art on the AVA and AADB datasets across three different tasks. The code is available at http://github.com/days1011/HLAGCN.

Item Type: Conference or Workshop Item (Paper)
Date Type: Published Online
Status: In Press
Schools: Computer Science & Informatics
Publisher: IEEE
ISBN: 9781665445108
ISSN: 2575-7075
Related URLs:
Date of First Compliant Deposit: 20 April 2021
Date of Acceptance: 3 March 2021
Last Modified: 04 Nov 2022 15:40
URI: https://orca.cardiff.ac.uk/id/eprint/140564

Citation Data

Cited 6 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics