Artwork style transfer model using deep learning approach

Hien, Ngo Le Huy; Huy, Luu Van; Hieu, Nguyen Van

doi:10.35470/2226-4116-2021-10-3-127-137

Cited by 10 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the use of NST-generated stimuli for aesthetic research has several shortcomings. (1) Although the computational paradigms underlying NST are relatively well defined and understood ( Semmo et al, 2017 ; Kotovenko et al, 2019 ; Hien et al, 2021 ), it is less well known how objective (physical) image properties are modulated by NST and how they mediate the aesthetic attributes and the liking of the generated images ( Zhang et al, 2021 ). (2) The responses of beholders may be biased against computer-generated art ( Chamberlain et al, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

Statistical image properties predict aesthetic ratings in abstract paintings created by neural style transfer

et al. 2022

View full text Add to dashboard Cite

Artificial intelligence has emerged as a powerful computational tool to create artworks. One application is Neural Style Transfer, which allows to transfer the style of one image, such as a painting, onto the content of another image, such as a photograph. In the present study, we ask how Neural Style Transfer affects objective image properties and how beholders perceive the novel (style-transferred) stimuli. In order to focus on the subjective perception of artistic style, we minimized the confounding effect of cognitive processing by eliminating all representational content from the input images. To this aim, we transferred the styles of 25 diverse abstract paintings onto 150 colored random-phase patterns with six different Fourier spectral slopes. This procedure resulted in 150 style-transferred stimuli. We then computed eight statistical image properties (complexity, self-similarity, edge-orientation entropy, variances of neural network features, and color statistics) for each image. In a rating study, we asked participants to evaluate the images along three aesthetic dimensions (Pleasing, Harmonious, and Interesting). Results demonstrate that not only objective image properties, but also subjective aesthetic preferences transferred from the original artworks onto the style-transferred images. The image properties of the style-transferred images explain 50 – 69% of the variance in the ratings. In the multidimensional space of statistical image properties, participants considered style-transferred images to be more Pleasing and Interesting if they were closer to a “sweet spot” where traditional Western paintings (JenAesthetics dataset) are represented. We conclude that NST is a useful tool to create novel artistic stimuli that preserve the image properties of the input style images. In the novel stimuli, we found a strong relationship between statistical image properties and subjective ratings, suggesting a prominent role of perceptual processing in the aesthetic evaluation of abstract images.

show abstract

Section: Introductionmentioning

confidence: 99%

Statistical image properties predict aesthetic ratings in abstract paintings created by neural style transfer

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The organization of the visual cortex and the human brain's neural network both had an influence on CNN's architecture [54]. Individual neurons can only respond to stimuli in the restricted visual field region known as the Receptive Field.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

A Deep Learning Model for Context Understanding in Recommendation Systems

Hien,

Huy,

Manh

et al. 2024

IJCAI

View full text Add to dashboard Cite

Due to the robust growth in the amount of data and Internet users, there has been a significant rise in information overload, hindering timely access to user demand. While information retrieval systems, such as Google, Bing, and Altavista have partially addressed this challenge, prioritization and personalization of information have yet to be fully implemented. Therefore, recommendation systems are developed to resolve the issue by filtering and segmenting important information from an enormous volume of data based on different criteria such as preferences, interests, and user behaviors. By collecting data on users' interests and purchased products, the system can predict whether a particular user would enjoy an item, thus delivering an appropriate suggestion strategy. However, the increased number of Internet users and items has resulted in sparseness in increasingly vast datasets, reducing the performance of recommendation algorithms. Therefore, this study developed a model integrating Convolutional Neural Network (CNN) and Matrix Factorization (MF) to add extra product and user information, extract contexts, and add bias to the observed ratings in the training process, attempting to enhance the recommendation accuracy and context understanding. This approach can take advantage of CNN to efficiently capture an image's or document's local features, with the combination of MF to create relationships between 2 main entities, users and items. The proposed model obtained the highest RMSE of 0.93 when predicting favorable movies for 4,000 users, with an ability to learn complex contextual features and suggest more relevant content. The results are promising and can act as a reference for developing context understanding in recommendation systems, and future work may focus on optimizing the performance and developing more text-processing techniques.Povzetek: Razvit je nov model globokega učenja, ki združuje konvolucijske nevronske mreže (CNN) in matrično faktorizacijo (MF) za izboljšanje natančnosti in razumevanja konteksta v priporočilnih sistemih.

show abstract

“…Notably, the Logarithmic Regression with Exponential Transformation model generates negative R squared values in all cases, implying that the goodness of fit level is worse than fitting the curve of the model. [41,42] has been employed in this study to estimate the total CO 2 emissions and fuel consumption of vehicles from multiple inputs. CNN is a form of deep neural network that is often used to explore visual imagery [37,43].…”

Section: Linear Regression and Univariate Polynomial Regressionmentioning

confidence: 99%

Analysis and Prediction Model of Fuel Consumption and Carbon Dioxide Emissions of Light-Duty Vehicles

Hien

Kor

2022

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Due to the alarming rate of climate change, fuel consumption and emission estimates are critical in determining the effects of materials and stringent emission control strategies. In this research, an analytical and predictive study has been conducted using the Government of Canada dataset, containing 4973 light-duty vehicles observed from 2017 to 2021, delivering a comparative view of different brands and vehicle models by their fuel consumption and carbon dioxide emissions. Based on the findings of the statistical data analysis, this study makes evidence-based recommendations to both vehicle users and producers to reduce their environmental impacts. Additionally, Convolutional Neural Networks (CNN) and various regression models have been built to estimate fuel consumption and carbon dioxide emissions for future vehicle designs. This study reveals that the Univariate Polynomial Regression model is the best model for predictions from one vehicle feature input, with up to 98.6% accuracy. Multiple Linear Regression and Multivariate Polynomial Regression are good models for predictions from multiple vehicle feature inputs, with approximately 75% accuracy. Convolutional Neural Network is also a promising method for prediction because of its stable and high accuracy of around 70%. The results contribute to the quantifying process of energy cost and air pollution caused by transportation, followed by proposing relevant recommendations for both vehicle users and producers. Future research should aim towards developing higher performance models and larger datasets for building APIs and applications.

show abstract

Artwork style transfer model using deep learning approach

Cited by 10 publications

References 19 publications

Statistical image properties predict aesthetic ratings in abstract paintings created by neural style transfer

Statistical image properties predict aesthetic ratings in abstract paintings created by neural style transfer

A Deep Learning Model for Context Understanding in Recommendation Systems

Analysis and Prediction Model of Fuel Consumption and Carbon Dioxide Emissions of Light-Duty Vehicles

Contact Info

Product

Resources

About