scholarly journals Self-relevance predicts the aesthetic appeal of real and synthetic artworks generated via neural style transfer

2021 ◽  
Author(s):  
Edward A. Vessel ◽  
Laura Beatriz Borges Bastos Pasqualette ◽  
Cem Uran ◽  
Sara Koldehoff ◽  
Martin Vinck
Keyword(s):  
Deep Neural Networks ◽  
Matched Control ◽  
Large Fraction ◽  
Image Features ◽  
Autobiographical Memories ◽  
Style Transfer ◽  
Self Identity ◽  
Aesthetic Appeal ◽  
The Aesthetic ◽  
Artistic Skill

What determines the aesthetic appeal of artworks? Recent work suggests that aesthetic appeal can to some extent be predicted from a visual artwork’s image features. Yet, a large fraction of variance in aesthetic ratings remains unexplained and may relate to individual preferences. We hypothesized that an artwork’s aesthetic appeal depends strongly on self-relevance. In a first experiment, observers viewed real artworks and rated them for aesthetic appeal and self-relevance. Aesthetic appeal was positively predicted by self-relevance. In a second experiment, we developed a method to create synthetic, self-relevant artworks, by using deep neural networks that transferred the style of exist- ing artworks to photographs. Style transfer was applied to self-relevant photographs which were identified based on autobiographical memories, self-identity, interests, common activities and pref- erences. Self-relevant, synthetic artworks were rated as more aesthetically appealing than matched control images, at a level similar to real artworks. Thus, self-relevance is a key determinant of aesthetic appeal, independent of artistic skill and image features.

The Riddle of the Sands

2017 ◽  
Author(s):  
Daniel Brayton
Keyword(s):  
Coastal Zone ◽  
North Atlantic ◽  
Intertidal Zone ◽  
Nation State ◽  
Narrative Fiction ◽  
Aesthetic Appeal ◽  
Secret Service ◽  
German Coast ◽  
The Aesthetic ◽  
Modern Nation State

The aesthetic appeal of coasts is due in part to the indeterminacy of the intertidal zone. The imagination finds room to play where land and sea meet. This chapter explores the coastal zone that lies at the heart of a novel considered by many to be the first modern spy thriller, Erskine Childers’s The Riddle of the Sands: A Record of Secret Service. Childers develops the notion of coastal indeterminacy as a figure for the boundaries, ambitions, and limitations of the modern nation-state. The journey of Childers’s characters through a north Atlantic archipelago that extends from the German coast draws a line of association between Europe and Britain, whose form depends on coastlines, estuaries, and shallows. In following this course, Childers creates a narrative fiction that shifts between charts, borders, and languages.

scholarly journals Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Lorena Escudero Sanchez ◽  
Leonardo Rundo ◽  
Andrew B. Gill ◽  
Matthew Hoare ◽  
Eva Mendes Serrao ◽  
...  
Keyword(s):  
Large Fraction ◽  
Therapy Response ◽  
Response Assessment ◽  
Ct Images ◽  
Optimal Number ◽  
Image Features ◽  
Liver Tumour ◽  
Slice Thickness ◽  
Invasive Method ◽  
Feature Values

AbstractRadiomic image features are becoming a promising non-invasive method to obtain quantitative measurements for tumour classification and therapy response assessment in oncological research. However, despite its increasingly established application, there is a need for standardisation criteria and further validation of feature robustness with respect to imaging acquisition parameters. In this paper, the robustness of radiomic features extracted from computed tomography (CT) images is evaluated for liver tumour and muscle, comparing the values of the features in images reconstructed with two different slice thicknesses of 2.0 mm and 5.0 mm. Novel approaches are presented to address the intrinsic dependencies of texture radiomic features, choosing the optimal number of grey levels and correcting for the dependency on volume. With the optimal values and corrections, feature values are compared across thicknesses to identify reproducible features. Normalisation using muscle regions is also described as an alternative approach. With either method, a large fraction of features (75–90%) was found to be highly robust (< 25% difference). The analyses were performed on a homogeneous CT dataset of 43 patients with hepatocellular carcinoma, and consistent results were obtained for both tumour and muscle tissue. Finally, recommended guidelines are included for radiomic studies using variable slice thickness.

scholarly journals GIS-Based Aesthetic Appraisal of Short-Range Viewsheds of Coastal Dune and Forest Landscapes

Forests ◽  
2021 ◽  
Vol 12 (11) ◽  
pp. 1534
Author(s):  
Arvydas Urbis ◽  
Ramūnas Povilanskas ◽  
Egidijus Jurkus ◽  
Julius Taminskas ◽  
Domantas Urbis
Keyword(s):  
Spatial Variation ◽  
Short Range ◽  
Coastal Dune ◽  
Geographical Information ◽  
Coastal Forests ◽  
Scenic Beauty ◽  
Aesthetic Appeal ◽  
High Conservation ◽  
The Aesthetic ◽  
Management Alternatives

This paper demonstrates the possibilities of a Geographical Information System (GIS) for investigating and explicating the spatial variation of the short-range viewshed aesthetic appeal in a World Heritage coastal dune and forest area. The study pursues the following objectives: (1) develop and trial a GIS-based algorithm for computing the Aesthetic Appeal Index for a Short-Range Viewshed (ǣ); (2) deliver an output map showing the spatial variation of the computed ǣ values in the target territory and distribution of the zones with high scenic quality and potential aesthetic ecosystem services (PAES); and (3) assess management alternatives in zones with high PAES and high conservation value. This study combines two key innovative aspects. First, it integrates an objective digital map of habitats with subjective scenic preferences of coastal forest and dune landscapes based on psychophysical and cognitive perceptions of scenic beauty. Second, it applies a GIS-based algorithm to translate subjective scenic preferences to an output map of ǣ. The study’s main conclusion is that the combined aesthetic appraisal of the immediate and foreground viewshed of coastal forests and dunes, by applying a specially created GIS algorithm, allows an assessment of the scenic quality of this landscape reliably in statistical terms.

scholarly journals Semantic representation for visual reasoning

2019 ◽  
Vol 277 ◽  
pp. 02006 ◽  
Author(s):  
Xubin Ni ◽  
Lirong Yin ◽  
Xiaobing Chen ◽  
Shan Liu ◽  
Bo Yang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Semantic Representation ◽  
Image Features ◽  
Gram Matrix ◽  
Human Reasoning ◽  
Style Transfer ◽  
Related Information ◽  
Abstract Description ◽  
High Level ◽  
Regular Networks

In the field of visual reasoning, image features are widely used as the input of neural networks to get answers. However, image features are too redundant to learn accurate characterizations for regular networks. While in human reasoning, abstract description is usually constructed to avoid irrelevant details. Inspired by this, a higher-level representation named semantic representation is introduced in this paper to make visual reasoning more efficient. The idea of the Gram matrix used in the neural style transfer research is transferred here to build a relation matrix which enables the related information between objects to be better represented. The model using semantic representation as input outperforms the same model using image features as input which verifies that more accurate results can be obtained through the introduction of high-level semantic representation in the field of visual reasoning.

scholarly journals Nanotechnology-Based Cosmeceuticals

2014 ◽  
Vol 2014 ◽  
pp. 1-14 ◽  
Author(s):  
Alka Lohani ◽  
Anurag Verma ◽  
Himanshi Joshi ◽  
Niti Yadav ◽  
Neha Karki
Keyword(s):  
Human Health ◽  
Potential Risk ◽  
Molecular Level ◽  
Personal Care ◽  
Active Ingredients ◽  
New Techniques ◽  
Aesthetic Appeal ◽  
Care Industry ◽  
The Aesthetic ◽  
Opening Up

Cosmeceuticals are the fastest growing segment of the personal care industry, and a number of topical cosmeceutical treatments for conditions such as photoaging, hyperpigmentation, wrinkles, and hair damage have come into widespread use. In the cosmeceutical arena nanotechnology has played an important role. Using new techniques to manipulate matter at an atomic or molecular level, they have been at the root of numerous innovations, opening up new perspectives for the future of cosmeceutical industry. Nanotechnology-based cosmeceuticals offer the advantage of diversity in products, and increased bioavailability of active ingredients and increase the aesthetic appeal of cosmeceutical products with prolonged effects. However increased use of nanotechnology in cosmeceuticals has raised concern about the possible penetration of nanoparticles through the skin and potential hazards to the human health. This review outlines the different nanoparticles used in various classes of cosmeceuticals, nanotechnology-based cosmeceutical products present in the market, and the potential risk caused by nanoparticles on exposure and recent regulatory steps taken to overcome them.

Polymerization Stress and the Influence of TOSU Addends on Methacrylate Composites

2012 ◽  
Author(s):  
Ryan R. Holmes ◽  
Jennifer R. Melander ◽  
Rachel A. Weiler ◽  
Thomas P. Schuman ◽  
Kathleen V. Kilway ◽  
...  
Keyword(s):  
Composite Resin ◽  
Mechanical Strain ◽  
Degree Of Conversion ◽  
Double Bonds ◽  
Gap Formation ◽  
Premature Failure ◽  
Aesthetic Appeal ◽  
Marginal Integrity ◽  
The Aesthetic ◽  
High Degree

The aesthetic appeal of composite-resin restoratives promotes their use, however their functional life is significantly shorter when compared to their metal counterparts.1 One possible reason is the effect of polymerization stress on marginal integrity. Shrinkage of the composite, and its associated stress, has been found to cause gap formation and stress interactions between the restorative and the adhesive. These gaps offer an ideal niche for bacteria, and, when compounded by the mechanical strain of chewing, can lead to premature failure of the restorative.2,3 Additionally, it is well known that incomplete conversion of the double bonds occurs during methacrylate polymerizations.4–7 A high degree of conversion is needed to prevent the presence of potentially hazardous monomers.8

Determining the Aesthetic Appeal of Astronomical Images

Leonardo ◽  
2015 ◽  
Vol 48 (1) ◽  
pp. 70-71 ◽  
Author(s):  
Lars Lindberg Christensen ◽  
Douglas Pierce-Price ◽  
Olivier Hainaut
Keyword(s):  
Astronomy Education ◽  
Aesthetic Appeal ◽  
Astronomical Image ◽  
Education And Outreach ◽  
Astronomical Images ◽  
The Aesthetic

In the context of images used for astronomy education and outreach purposes, this paper describes a set of parameters that are key in determining the aesthetic appeal, or beauty — and therefore effectiveness— of an astronomical image.

Measuring the Aesthetic Appeal of Textiles1

1965 ◽  
Vol 35 (5) ◽  
pp. 428-434 ◽  
Author(s):  
R.M. Hoffman
Keyword(s):  
Aesthetic Appeal ◽  
The Aesthetic

scholarly journals High-Capacity Image Steganography Algorithm Based on Image Style Transfer

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Xinliang Bi ◽  
Xiaoyuan Yang ◽  
Chao Wang ◽  
Jia Liu
Keyword(s):  
High Capacity ◽  
Image Features ◽  
Image Steganography ◽  
Cover Image ◽  
Secret Message ◽  
The Internet ◽  
Stego Image ◽  
Style Transfer ◽  
Secret Image ◽  
Secret Information

Steganography is a technique for publicly transmitting secret information through a cover. Most of the existing steganography algorithms are based on modifying the cover image, generating a stego image that is very similar to the cover image but has different pixel values, or establishing a mapping relationship between the stego image and the secret message. Attackers will discover the existence of secret communications from these modifications or differences. In order to solve this problem, we propose a steganography algorithm ISTNet based on image style transfer, which can convert a cover image into another stego image with a completely different style. We have improved the decoder so that the secret image features can be fused with style features in a variety of sizes to improve the accuracy of secret image extraction. The algorithm has the functions of image steganography and image style transfer at the same time, and the images it generates are both stego images and stylized images. Attackers will pay more attention to the style transfer side of the algorithm, but it is difficult to find the steganography side. Experiments show that our algorithm effectively increases the steganography capacity from 0.06 bpp to 8 bpp, and the generated stylized images are not significantly different from the stylized images on the Internet.

scholarly journals Specific Area Style Transfer on Real-Time Video

2021 ◽  
Vol 10 (5) ◽  
pp. 50-56
Author(s):  
Hyung-Hwa Ko ◽  
GeunTae Kim ◽  
Hyunmin Kim
Keyword(s):  
Real Time ◽  
Deep Neural Networks ◽  
Specific Area ◽  
Image Generation ◽  
Style Transfer ◽  
Real Time Processing ◽  
Time Processing ◽  
Related Research ◽  
City Street ◽  
Speed And Accuracy

Since deep learning applications in object recognition, object detection, segmentation, and image generation are needed increasingly, related research has been actively conducted. In this paper, using segmentation and style transfer together, a method of producing desired images in the desired area in real-time video is proposed. Two deep neural networks were used to enable as possible as in real-time with the trade-off relationship between speed and accuracy. Modified BiSeNet for segmentation and CycleGAN for style transfer were processed on a desktop PC equipped with two RTX-2080-Ti GPU boards. This enables real-time processing over SD video in decent level. We obtained good results in subjective quality to segment Road area in city street video and change into the Grass style at no less than 6(fps).

Sign in / Sign up

Export Citation Format

Share Document