Learning image aesthetic subjectivity from attribute-aware relational reasoning network

Zhu, Hancheng; Zhou, Yong; Yao, Rui; Wang, Guangcheng; Yang, Yuzhe

doi:10.1016/j.patrec.2022.02.008

Cited by 9 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates that it is more efficient to embed image aspect ratios in the Transformer with higher input resolutions. For the binary classification, although several CNN-based IQA methods (PA_IAA [38], HLA-GCN [35] and Zhu et al [36]) are better than the Transformerbased IQA methods (MUSIQ [10] and our method), ARET-IQA (384) still outperforms MUSIQ by 2.1%. This demonstrates that the proposed ARET-IQA is more effective in evaluating image aesthetic quality by using a simple aspect-ratio-embedding strategy instead of directly learning the massive original image patches in the Transformer network.…”

Section: Acc (%)↑ Plcc ↑ Srcc ↑ Emd ↓mentioning

confidence: 71%

“…In recent years, with the popularity of social media and photography, people have begun to pay attention to the aesthetic aspects of images. Hence, researchers have proposed many AQA methods that can predict the aesthetics of images, including handcrafted feature-based methods [11,15] and deep-learning-based methods [34][35][36].…”

Section: Image Quality Assessmentmentioning

confidence: 99%

“…Murray et al [11] 68.0 ---RAPID [34] 74.5 ---A-Lamp [39] 82.5 ---Kong et al [21] 77.3 -0.558 -NIMA [9] 81.5 0.636 0.612 0.050 PA_IAA [38] 83.7 0.678 0.677 0.047 Zeng et al [22] 80.8 0.720 0.719 0.0650 AFDC [25] 83.0 0.671 0.649 0.045 MUSIQ [10] 81.5 0.738 0.726 -HLA-GCN [35] 84.6 0.687 0.665 0.043 Zhu et al [36] 85 As shown in the table, the proposed ARET-IQA delivers better performance than the other IQA methods in the tasks of score regression and distribution prediction, which also demonstrates the effectiveness of our method in aesthetic quality assessment by learning the aspect ratios of images in the Transformer network. Compared with ARET-IQA (224), the improvement of ARET-IQA (384) on SRCC and PLCC is 1.3% and 1.5%, respectively.…”

Section: Acc (%)↑ Plcc ↑ Srcc ↑ Emd ↓mentioning

confidence: 99%

See 2 more Smart Citations

ARET-IQA: An Aspect-Ratio-Embedded Transformer for Image Quality Assessment

et al. 2022

Self Cite

View full text Add to dashboard Cite

Image quality assessment (IQA) aims to automatically evaluate image perceptual quality by simulating the human visual system, which is an important research topic in the field of image processing and computer vision. Although existing deep-learning-based IQA models have achieved significant success, these IQA models usually require input images with a fixed size, which varies the perceptual quality of images. To this end, this paper proposes an aspect-ratio-embedded Transformer-based image quality assessment method, which can implant the adaptive aspect ratios of input images into the multihead self-attention module of the Swin Transformer. In this way, the proposed IQA model can not only relieve the variety of perceptual quality caused by size changes in input images but also leverage more global content correlations to infer image perceptual quality. Furthermore, to comprehensively capture the impact of low-level and high-level features on image quality, the proposed IQA model combines the output features of multistage Transformer blocks for jointly inferring image quality. Experimental results on multiple IQA databases show that the proposed IQA method is superior to state-of-the-art methods for assessing image technical and aesthetic quality.

show abstract

Section: Acc (%)↑ Plcc ↑ Srcc ↑ Emd ↓mentioning

confidence: 71%

Section: Image Quality Assessmentmentioning

confidence: 99%

Section: Acc (%)↑ Plcc ↑ Srcc ↑ Emd ↓mentioning

confidence: 99%

See 1 more Smart Citation

ARET-IQA: An Aspect-Ratio-Embedded Transformer for Image Quality Assessment

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The applicability of this framework is not confined to traditional consumer behavior research but extends to the realm of online consumer behavior, as observed by Zhu et al (2022). The SOR framework convincingly argues that image features serve as stimuli that activate individuals' perceptions.…”

Section: Literature Review and Hypothesis Developmentmentioning

confidence: 81%

Images’ features and Airbnb listing price: the mediation effect of visual aesthetic perception

Hu,

Lin,

Liu

et al. 2023

View full text Add to dashboard Cite

Purpose This study aims to explore image-based visual price determinants (image features and visual aesthetic perception) and how image features affect Airbnb listing price on a sharing accommodation platform. Design/methodology/approach The study uses an SOR model and a hedonic price model to examine the connections between the characteristics of image features, visual aesthetic perception and Airbnb listing prices. The model is then examined by an econometric model using data from Insideairbnb.com. Findings Empirical results revealed that image features have a significant positive effect on visual aesthetic perception, visual aesthetic perception has a significant positive effect on Airbnb listing price and visual aesthetic perception has a significant mediating effect between image features and Airbnb listing price. Originality/value This study contributes to the relationship and effect mechanism among image features, visual aesthetic perception and Airbnb listing price and has some implications for both property operators and the sharing accommodation platform.

show abstract

“…Aesthetic quality assessment is still a very trending research area, as many models are still developed nowadays and presented in different papers. [10][11][12][13] However, as our work do not consist in devising a new aesthetic quality assessment model, we do not focus this section on these papers. Very few studies on the relevance of training datasets for aesthetics assessment have already been conducted.…”

Section: Related Workmentioning

confidence: 99%

Deep learning for assessing the aesthetics of professional photographs

Chambe

Cozot

Meur

2022

Computer Animation & Virtual

View full text Add to dashboard Cite

Aesthetic quality assessment for photographs is an important research topic since it can be used for a number of applications, such as image database management or image browsing. In 2012, the aesthetic visual analysis (AVA) dataset has been proposed. It has since then been used to train the majority of computational models of aesthetics assessment. We observe that AVA is mainly composed of competitive photographs which notion of aesthetics differs from other kinds of photographs, such as professional photographs. In this paper, we evaluate whether or not recent aesthetics assessment models generalize well and perform well over professional photographs. We noticed that the different models we tested behave differently on both categories, and therefore do not generalize well. Besides, we fine‐tuned one of the tested model using professional photographs and the results show that this fine‐tuning is effectively improving the coverage of the methods.

show abstract

Learning image aesthetic subjectivity from attribute-aware relational reasoning network

Cited by 9 publications

References 12 publications

ARET-IQA: An Aspect-Ratio-Embedded Transformer for Image Quality Assessment

ARET-IQA: An Aspect-Ratio-Embedded Transformer for Image Quality Assessment

Images’ features and Airbnb listing price: the mediation effect of visual aesthetic perception

Deep learning for assessing the aesthetics of professional photographs

Contact Info

Product

Resources

About