Transformers in computational visual media: A survey

Y Xu, H Wei, M Lin, Y Deng, K Sheng, M Zhang… - Computational Visual …, 2022 - Springer
Transformers, the dominant architecture for natural language processing, have also recently
attracted much attention from computational visual media researchers due to their capacity …

Artificial neural networks and deep learning in the visual arts: A review

I Santos, L Castro, N Rodriguez-Fernandez… - Neural Computing and …, 2021 - Springer
In this article, we perform an exhaustive analysis of the use of Artificial Neural Networks and
Deep Learning in the Visual Arts. We begin by introducing changes in Artificial Intelligence …

Hierarchical layout-aware graph convolutional network for unified aesthetics assessment

D She, YK Lai, G Yi, K Xu - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
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 …

Towards artistic image aesthetics assessment: a large-scale dataset and a new method

R Yi, H Tian, Z Gu, YK Lai… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Image aesthetics assessment (IAA) is a challenging task due to its highly subjective nature.
Most of the current studies rely on large-scale datasets (eg, AVA and AADB) to learn a …

IC9600: a benchmark dataset for automatic image complexity assessment

T Feng, Y Zhai, J Yang, J Liang, DP Fan… - … on Pattern Analysis …, 2022 - ieeexplore.ieee.org
Image complexity (IC) is an essential visual perception for human beings to understand an
image. However, explicitly evaluating the IC is challenging, and has long been overlooked …

A comprehensive survey on computational aesthetic evaluation of visual art images: Metrics and challenges

J Zhang, Y Miao, J Yu - IEEE Access, 2021 - ieeexplore.ieee.org
Computational image aesthetic evaluation is a computable human aesthetic perception and
judgment realized by machines, which has a significant impact on a variety of applications …

Self-supervised multi-task pretraining improves image aesthetic assessment

J Pfister, K Kobs, A Hotho - … of the IEEE/CVF Conference on …, 2021 - openaccess.thecvf.com
Abstract Neural networks for Image Aesthetic Assessment are usually initialized with weights
of pretrained ImageNet models and then trained using a labeled image aesthetics dataset …

Self-supervised feature augmentation for large image object detection

X Pan, F Tang, W Dong, Y Gu, Z Song… - … on Image Processing, 2020 - ieeexplore.ieee.org
Input scale plays an important role in modern detection frameworks, and an optimal training
scale for images exists empirically. However, the optimal one usually cannot be reached in …

Privileged multi-task learning for attribute-aware aesthetic assessment

Y Shu, Q Li, L Liu, G Xu - Pattern Recognition, 2022 - Elsevier
Aesthetic attributes are crucial for aesthetics because they explicitly present some photo
quality cues that a human expert might use to evaluate a photo's aesthetic quality. However …

Multi-output learning based on multimodal GCN and co-attention for image aesthetics and emotion analysis

H Miao, Y Zhang, D Wang, S Feng - Mathematics, 2021 - mdpi.com
With the development of social networks and intelligent terminals, it is becoming more
convenient to share and acquire images. The massive growth of the number of social …