Artistic Style Research Articles

Artionyms and machine learning: auto naming of the paintings

Image captioning is a question of great interest in a wide range of applications. In the art market there is a particularly acute shortage of specialized machine learning methods for accelerated and at the same time in-depth study of often too specific aspects of art. One of the main difficulties is caused by ambiguous names of art works, as well as clarifying (in practice, often complicating under- standing and perception) signatures of the authors to them. Although previous research has established that captioning of photos can be done with high efficacy, there is little published data about generation of captions for artistic paintings. In this research, we utilize a transformer architecture to generate an artionym for a given painting in author’s manner. We describe the model and report its performance on different art styles. We assess the model performance with an expert evaluation and image captioning metrics, and then discuss their capacity to analyze art-related names.

Stacking-based ensemble learning for identifying artist signatures on paintings

Identifying artist signatures on paintings is essential for authenticating artworks and advancing digital humanities. An artist’s signature is a consistent element included in each painting that the artist creates, providing a unique identifier for their work. Traditional methods that rely on expert analysis and manual comparison are time-consuming and are prone to human error. Although convolutional neural networks (CNNs) have shown promise in automating this process, existing single-model approaches struggle with the diversity and complexity of artistic styles, leading to limitations in their performance and generalizability. Therefore, this study proposes an ensemble learning approach that integrates the predictive power of multiple CNN-based models. The proposed framework leverages the strengths of three state-of-the-art CNNs: EfficientNetB4, ResNet-50, and Xception. These models were independently trained, and the predictions were combined using a meta-learning strategy. To address class imbalance, data augmentation techniques and weighted loss functions were employed. The experimental results obtained on a dataset of more than 8,000 paintings from 50 artists demonstrate significant improvements over individual CNN architectures and other ensemble methods, thereby effectively capturing complex features and improving generalizability.

Features of the representation of architectural space in the painting works of Giorgio de Chirico

This article describes the features of the depiction of architectural space in the paintings of the surrealist artist Giorgio de Chirico. In general terms, surrealism is described as an artistic style of the early twentieth century, its emergence, distinctive features and semantic tasks; The questions in relation to Giorgio de Chirico are examined in more detail: from what architectural objects and constituent elements is the urban space of his paintings formed, what objects are the main semantic parts, the general universal architectural model of the formation of such a space in de Chirico’s compositions is described. The article describes the semiotic structure used by the master, reveals the concept and meaning of the term “metaphysical painting”, ways of reading a surreal work of art, and the playful nature of the interaction between the artist and the viewer. The article analyzes in detail the methods and features of constructing the internal space of the metaphysical works of this master, showing the constituent elements, methods, techniques, and techniques for organizing the composition of the painting. The significance of the image of architectural space in de Chirico’s works on modern man and the use of his artistic experience in our time is described.

Learning-based Artificial Intelligence Artwork: Methodology Taxonomy and Quality Evaluation

With the development of the theory and technology of computer science, machine or computer painting is increasingly being explored in the creation of art. Machine-made works are referred to as artificial intelligence (AI) artworks. Early methods of AI artwork generation have been classified as non-photorealistic rendering, and, latterly, neural style transfer methods have also been investigated. As technology advances, the variety of machine-generated artworks and the methods used to create them have proliferated. However, there is no unified and comprehensive system to classify and evaluate these works. To date, no work has generalized methods of creating AI artwork including learning-based methods for painting or drawing. Moreover, the taxonomy, evaluation, and development of AI artwork methods face many challenges. This article is motivated by these considerations. We first investigate current learning-based methods for making AI artworks and classify the methods according to art styles. Furthermore, we propose a consistent evaluation system for AI artworks and conduct a user study to evaluate the proposed system on different AI artworks. This evaluation system uses six criteria: beauty, color, texture, content detail, line, and style. The user study demonstrates that the six-dimensional evaluation index is effective for different types of AI artworks.

Neural Style Transfer, Creating Art with Deep Learning

Abstract—Neural style transfer is a deep learning technique that is the topic of study in this research paper. In NST two images are combined, a content and a style image. Where, while retaining the content image the artistic style of style image is imposed on the content image. In this research, a series of ways are explored to improve the efficiency and visual quality of the generated image. This research is about improvising and molding the existing losses, to improve the existing methodologies. Key contributions are dynamic weighting of content and style losses, multi scale loss computation for preserving the details in a better way. This kind of loss improvisation and changing is being used, so that not only the high-level structures and fine details are maintained in the image generated. These dynamic and multiple kind of losses will be implemented to retain the essence of the content in the content image. While generating a new image the content or style is overcompensated and most of the time one of these is having a stronger effect on the final image in most of the techniques, our motive is to eradicate the same and generate an excellent image. Along with this, various optimization techniques are studied in the underlying paper to compensate this computation cost of the newly introduced losses. The ways provide a framework for a neural style transfer with a higher quality and efficient combining of images. Index Terms—NST (Neural style transfer), dynamic weighting, multi-scale losses.

Spatial Characteristics of Everyday Life in The Tale of a Sister by M. A. Osorgin

Purpose. The article deals with the spatial characteristics of everyday life in The Tale of a Sister by M. A. Osorgin.Results. The analysis of the space of everyday life in the story identified several key locations: the parents’ house, Lisa’s apartment after her marriage, Evgeny Karlovitch’s and Katya’s house. The closet is an important place for little Kostya. That is where the secret of the strong friendship between the protagonist and his elder sister was born. The author’s emphasis on the sound component is noticeable along with the absence of bright colors in the depiction of the everyday space. The ordinariness in the story most often flows silently, and unusual events are described by sound characteristics.Conclusion. The image of everyday space in The Tale of a Sister has characteristic techniques used by the author. These are minimal detailing, lack of bright colors, and an emphasis on sounds, in particular. The minimal detailing might be the specific artistic style of M. A. Osorgin’s story. Despite the limited amount of descriptive details, the author creates a convex and tangible picture of the everyday life at that time, which fits organically into the struc-ture of the story and reflects the peculiarities of the characters’ lives.

Advancements and technical challenges in generative models of artificial intelligence painting

Abstract. Artificial Intelligence Painting, as a frontier field of AI technology application, has gained wide attention and rapid development in recent years. With the advancement of generative models, especially the emergence of variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models, the ability of AI in art creation has significantly increased. These techniques not only enable computers to generate realistic images, but also to simulate complex artistic styles, opening up new possibilities for artistic creation. Nevertheless, how to maintain a high degree of complexity and realism in the generated images, how to improve the data quality to enhance the generalization ability of the model, how to solve the pattern collapse problem to improve the stability of the generation, and how to improve the efficiency while ensuring the quality of the generation are all key issues in the current research. In addition, with the continuous evolution of AI technology, the future development direction and potential applications are also worth exploring in depth. The paper aims to systematically analyze the generative models and their applications in AI painting, to deeply discuss the technical challenges faced, and to look forward to the future development prospects.

Advancing Text-to-Image Synthesis with GANs: Integrating CNNs, LSTMs, and Style Transfer Techniques

Abstract. This research pioneers a novel methodology for generating images from text by integrating Generative Adversarial Networks (GANs), Convolutional Neural Networks (CNNs), and Long Short-Term Memory (LSTM) networks, effectively bridging the semantic disparity between textual inputs and their visual representations. The proposed model integrates attention mechanisms to enhance semantic precision, making sure that generated images closely align with the provided text. Additionally, style transfer techniques are employed to infuse the images with artistic elements, thereby enriching their visual appeal and diversity. The methodology involves a multi-stage process: CNNs are utilized for feature extraction, LSTMs encode textual descriptions into contextually rich vectors, and style transfer is applied to incorporate artistic styles into the generated images. Extensive experiments demonstrate that the model excels in producing high-fidelity images that not only capture the essence of textual descriptions but also exhibit significant visual diversity. This research makes substantial contributions to the field of GAN-based image synthesis, offering a framework that advances both semantic accuracy and creative expression. The findings provide a solid foundation for future research and innovations in automated image generation, highlighting the potential for further improvements and applications across various domains.

AI-Assisted Restoration of Yangshao Painted Pottery Using LoRA and Stable Diffusion

This study is concerned with the restoration of painted pottery images from the Yangshao period. The objective is to enhance the efficiency and accuracy of the restoration process for complex pottery patterns. Conventional restoration techniques encounter difficulties in accurately and efficiently reconstructing intricate designs. To address this issue, the study proposes an AI-assisted restoration workflow that combines Stable Diffusion models (SD) with Low-Rank Adaptation (LoRA) technology. By training a LoRA model on a dataset of typical Yangshao painted pottery patterns and integrating image inpainting techniques, the accuracy and efficiency of the restoration process are enhanced. The results demonstrate that this method provides an effective restoration tool while maintaining consistency with the original artistic style, supporting the digital preservation of cultural heritage. This approach also offers archaeologists flexible restoration options, promoting the broader application and preservation of cultural heritage.

On the Dynamism of Paintings Through the Distribution of Edge Directions

The digitization of artworks has recently offered new computational perspectives on the study of art history. While much of the focus has been on classifying styles or identifying objects, the analysis of more abstract concepts, such as the perception of motion or dynamism in still images, remains largely unexplored. Semioticians and artists have long explored the representation of dynamism in still images, but they often did so through theoretical frameworks or visual techniques, without a quantitative approach to measuring it. This paper proposes a method for computing and comparing the dynamism of paintings through edge detection. Our approach is based on the idea that the dynamism of a painting can be quantified by analyzing the edges in the image, whose distribution can be used to identify patterns and trends across artists and movements. We demonstrate the applicability of our method in three key areas: studying the temporal evolution of dynamism across different artistic styles, as well as within the works of a single artist (Wassily Kandinsky), visualizing and clustering a large database of abstract paintings through PixPlot, and retrieving similarly dynamic images. We show that the dynamism of a painting can be effectively quantified and visualized using edge detection techniques, providing new insights into the study of visual culture.

Legacy of the Ancestors: Revitalization of the ‘Scythian Animal Style’ in Altaian Arts and Crafts

This study examines the so-called ‘Scythian animal style’, which has experienced a revival, particularly in contemporary Altaian arts and crafts, where it serves as a symbolic expression of ethnic identity and the Altaians' identification with the ancient Pazyryk culture of the Iron Age. The animal motifs from the Pazyryk culture, originating in the Altai region, are widely incorporated by Altaian artisans today and are used to represent and promote Altaian culture. The paper focuses on the role of this art style in Altaian crafts, exploring its interpretation and the reasons for its use from the Altaians' perspective. Alongside professional literature, the study draws primarily on data gathered during the author's field research conducted in 2018 and 2019 in the Altai Republic, Russian Federation. The theoretical framework of the study is grounded in ethnosymbolism.

Rock art in the stone age of Gobustan: an archaeologist’s view

Gobustan is home to a large group of archaeological sites and many thousands of rock images dating from the Upper Palaeolithic to the Middle Ages. Due to its extraordinary scientific and artistic significance, the Gobustan complex is included in the UNESCO World Cultural Heritage List. This paper focuses on rock images dating back to the Stone Age. An attempt is made to systematize petroglyphs, taking into account their types, artistic styles, techniques of their creation, and themes of the images. The author considers relative dating and correlation of the distinguished styles with Gobustan sites of various stages of the Stone Age. Based on the analysis, style 1 of the region’s petroglyphs is dated from the first half of the Upper Palaeolithic (no later than 25–24 kya). Style 2 is synchronized with Mesolithic sites, and styles 3a and 3b are dated, with a certain degree of conditionality, from the Neolithic and Chalcolithic.

Religious, Cultural, and Modern Influences on Tibetan Thangka Paintings

This research paper explores how cultural, political, and religious contexts have shaped the tradition of Tibetan Thangka paintings. The Tibetan Thangka acts both as religious sacred objects and as an artwork. My interest in this subject began when I first saw a tangka painting in real life, and I was so curious about this art style which led me to further investigate this topic. This research paper analyzed journal articles, looked at many thangkas from different time periods in different styles, and interviewed Tibetan and non-Tibetan people about their perceptions of a few Thangka paintings with varied styles. This study found out that Tibetan thangkas have changed by a lot of influences globally and locally, including political influences of mainland China and the western cultural influences. This research highlights the importance of preserving the spiritual and the culture of the Tibetan Thangka paintings and acknowledges that some are slowly adapting to become more modern.

Study on the Aesthetic Value of Fang Wenshan’s Lyrics Creation

Fang Wenshan, a significant lyricist in the Chinese music industry, is renowned for his distinctive lyrical aesthetics. His lyrics seamlessly blend classical and modern elements, showcasing a rich array of expressive techniques and artistic styles from a linguistic perspective. By analyzing his works through the lenses of phonology, semantics, syntax, pragmatics, and rhetoric, we can uncover the unique aesthetics and linguistic features embedded in Fang Wenshan’s lyrics.

Modeling creativity in artificial intelligence: possibilities and limits

The article is dedicated to exploring the possibilities and limitations of developing creative artificial intelligence, particularly the ability of machines to determine the level of creativity in the objects they produce. To assess creativity, a three-step model of novelty is proposed, including ontological, subjective, and semantic levels. Three features of creative ideas or artifacts are identified: novelty, unexpectedness, and value. The article describes the model of a competitive generative network called "CAN: Creative Adversarial Networks," which creates new artistic styles and evaluates their novelty. The possibilities and limitations of modeling humor in creative artificial intelligence are discussed. The article analyzes examples of successful work by neural networks that generate jokes and write scripts, showing that the limitation of such systems is the machine's lack of a sense of context, space, and time. Additionally, a crucial condition for successfully writing jokes is the ability to laugh at them; humans can consciously choose the topic and format of humor, while machines lack their own goal-setting. It is shown that the technologies developed to date can be generalized as "weak creative artificial intelligence" since they can create new objects but are not capable of goal-setting and reflection. However, the possibilities of artificial intelligence are constantly expanding, changing our understanding of the limits of modeling natural intelligence.

Pectus excavatum or Pectus chiaroscurum in paintings of St. Jerome (17th century)?

Considering the influence of artistic style is a key methodological step in the iconodiagnostic process in order to avoid some pitfalls. The two present artworks, depicting Saint Jerome, attributed respectively to the 17th-century Neapolitan school and to Valentin de Boulogne, French painter of the 17th century, highlight how the interplay of light and shadow can enhance and disguise a possible pectus excvatum.

AnimeSketchNet: Integrating traditional sketching and anime art via an innovative dataset

Abstract. Recent advancements in text-to-image synthesis have shown promise, yet many models struggle with generalizability and adaptability, particularly in specialized genres like anime sketches. To overcome these challenges, we introduce AnimeSketchNet, a novel framework designed to enhance model performance by effectively capturing the complexity and stylistic variability unique to anime. AnimeSketchNet leverages a diverse collection of anime sketch styles with varying levels of detail, enabling the model to learn and adapt to the distinct artistic style of anime. Our dual-branch architecture, featuring a decoupled attention mechanism, seamlessly assimilates textual descriptions along with visual features, producing high-quality anime sketch that are both detailed and faithful the reference sketch. Experimental results demonstrate that AnimeSketchNet surpasses existing state-of-the-art models in both qualitative and quantitative evaluations. This work significantly advances text-to-image synthesis by offering a powerful and flexible tool tailored specifically to the unique demands of anime art.

Building a Chinese ancient architecture multimodal dataset combining image, annotation and style-model

In this rapidly evolving era of multimodal generation, diffusion models exhibit impressive generative capabilities, significantly enhancing the realm of creative image synthesis by intricately textual prompts. Yet, their effectiveness is limited in certain niche sectors, like depicting Chinese ancient architecture. This limitation is primarily due to the insufficient data that fails to encompass the unique architectural features and corresponding text information. Hence, we build an extensive multimodal dataset capturing the essence of Chinese architectures mostly from the Tang to the Yuan Dynasties. The dataset is categorized on the types, including image&text, video, and style models. In details, images and videos are methodically categorized based on locations. All images are annotated at two levels: initial annotations and descriptive terms based on distinctive characteristics and official information. Moreover, seven artistic styles fine-tuning models are provided in our dataset for further innovations. Significantly, this is the first Chinese ancient architecture dataset and the instance of using the Pinyin system to annotate unique terms related to Chinese architectural styles.

Synthesis of Arts by means of Sculpture Forms

The purpose of the work is to characterise the syncretism of sculptural forms in the development of monumental Ukrainian sculpture; emphasise the national features of the development of national sculpture on the example of the works of modern Ukrainian sculptors. The methodology of the work consists in the principles of holistic and systemic approaches to the study of the synthesis of arts in the sculptural forms of Ukrainian artists. An analytical method was applied to study scientific approaches to the synthesis of arts, as well as an artistic-stylistic method, as well as a system-functional method to the structuring of artistic works as a phenomenon of modern monumental sculpture. The scientific novelty of the study consists in the discourse on the synthesis of arts in the art history environment, characterising some works of art that belong to the category of monumental sculpture. Conclusions. It should be noted that in the Ukrainian art space there is a synthesis between classical forms and intermedia installations, which creates a complex and multi-layered context for modern artists. The perception of time, space and material becomes plastic and changeable, and this, in turn, stimulates the development of new aesthetic forms. Sculptural images have a significant influence on the formation of styles of young artists, where the emphasis is not only on silhouettes, but also on specific elements originating from various forms. Artists build associative visual sequences, embodying unrealistic, yet deeply symbolic images that resonate with viewers on an emotional level. In the examples from the workshops you mentioned, we see how a variety of materials and art forms and execution methods are used to create coherent and complete images that reflect the synthesis of different arts. The theme of the synthesis of arts in different sculptural forms, which sometimes seem completely incompatible, is indeed one of the most relevant for research.

Applications of AI in martial arts: A survey

Artificial intelligence (AI) has become an interdisciplinary subject that integrates digital image processing, machine learning, and computer science, etc. A lot of work in martial arts benefits from AI technology. In this paper, we highlight and summarize the applications of AI in martial arts and indicate the main progress of related studies. Through the investigation of martial arts styles, tasks, data acquisition methods, and algorithm improvements, a paradigm that represents a possible technological process for an intelligent martial arts training system was summarized. These applications bring more scientific training and more effective technical analysis to martial arts. Furthermore, this paper delves into specific AI applications in areas such as action recognition, pose estimation, action evaluation, elite athlete support, sports betting, health care, animation generation, and competition field segmentation. By exploring these areas, the research prospects of AI applications in martial arts are comprehensively discussed. This paper inspires further research on martial arts by using AI, which includes helping researchers expand their research ideas and research methods, identify frontier issues, and innovate based on existing research.