Hasil untuk "Art"

E. Kris

A. Barnes, N. Goodman

T. Murray

S. Hoogendoorn, P. Bovy

S. McNiff

O. Grau, Emily Gutheinz, Gloria Custance

O. Ashenfelter

Joseph W. Leonard

Anna Arkhipova, Pavel Hok, Pavel Hok et al.

Creativity has been consensually defined as an ability to produce novel and original ideas/works, a definition shared both by the general public and among scholars. Since creativity is one of the most important and unique cognitive constructs seen in human beings, ways to enhance creativity have fascinated researchers across a broad range of human knowledge domains - from the arts and the humanities to science and technology. The functional process of creativity has been actively discussed not only in psychology, but also in neuroscience, where research is uncovering its neural correlates. A great amount of neuroimaging research has focused on describing anatomical and functional adaptations in the brain following various types of cognitive learning and training, e.g., classes of visual art or music composition, courses of drawing, calligraphy or playing musical instruments. A consistent underlying mechanism of domain-specific creativity has not yet been revealed due to difficulties in defining creativity or due to lack of generalizability across different modalities. On the other hand, recent studies suggest that there is a relationship between domain-general creativity and functional connectivity in particular brain networks. In this review, we discuss whether there is evidence for brain plasticity induced by training in creativity and associated behavioral changes, as well as whether the observed brain changes are consistent with the studies of neurobiological underpinnings of creativity and the changes induced by cognitive training.

Lucy Jiang, Amy Seunghyun Lee, Jon E. Froehlich et al.

Public art can hold cultural, social, political, and aesthetic significance, enriching urban environments and promoting well-being. However, a majority of urban art is inaccessible to blind and low vision (BLV) people. Most art access research has focused on private and curated settings (e.g., museums, galleries) and most urban access work has centered on outdoor navigation, leaving urban and public art accessibility largely understudied. We conducted semi-structured interviews with 16 BLV participants, using design probes featuring AI-generated descriptions and real-time AI interactions to investigate preferences for both discovering and engaging with urban art. We found that BLV people valued spontaneous art exploration, multisensory (e.g., tactile, auditory, olfactory) engagement, and detailed descriptions of culturally significant artwork. Participants also highlighted challenges distinct to urban art contexts: safety took precedence over art exploration, multisensory access measures could be disruptive to others in the public space, and inaccurate AI descriptions could lead to cultural erasure. Our contributions include empirical insights on BLV preferences for urban art discovery and engagement, seven design dimensions for public art access solutions, and implications for expanding HCI urban accessibility research beyond navigation.

Sahil Wadhwa, Himanshu Kumar, Guanqun Yang et al.

Large Language Models (LLMs) are powerful candidates for complex decision-making, leveraging vast encoded knowledge and remarkable zero-shot abilities. However, their adoption in high-stakes environments is hindered by their opacity; their outputs lack faithful explanations and cannot be effectively contested to correct errors, undermining trustworthiness. In this paper, we propose ART (Adaptive Reasoning Trees), a hierarchical method for claim verification. The process begins with a root claim, which branches into supporting and attacking child arguments. An argument's strength is determined bottom-up via a pairwise tournament of its children, adjudicated by a judge LLM, allowing a final, transparent and contestable verdict to be systematically derived which is missing in methods like Chain-of-Thought (CoT). We empirically validate ART on multiple datasets, analyzing different argument generators and comparison strategies. Our findings show that ART's structured reasoning outperforms strong baselines, establishing a new benchmark for explainable claim verification which is more reliable and ensures clarity in the overall decision making step.

Kristen Wells, T. Battaglia, D. Dudley et al.

G. Weber, Peter Brusilovsky

A. Goshtasby, S. G. Nikolov

Fernando Echarri, Ignacio Miguéliz, Natalia Verea et al.

Contemporary art museums have become important learning environments to promote visitor aesthetic education. Each piece of art constantly sends different messages to the viewer and creates a person-art connection that can provide significant experiences. These connections can be established in the contemplation of the sublime. In order to understand how these connections occur, researchers present a study about the relationship between aesthetic experience and the sublime that can happen through the contemplation of contemporary art, both figurative and abstract. Specifically, this aesthetic experience with the sublime has been studied in a group of highly sensitive individuals. The abstract work of Mark Rothko's masterpiece “Untitled” (1969) and the figurative work of Fernando Maselli “Artificial Infinite” (2014) have been utilized. The study includes an instrument for the evaluation of the “aesthetic experience of the Sublime,” in which four dimensions—perception, emotion, cognition, and spiritual—are considered. This instrument has been applied to a group of highly sensitive people. Based on mixed quantitative and qualitative data analysis, results show that these individuals can experience contemporary art painting intensely by perceiving changes in its sensitive features while vanishing self-references of time and space.

Miloš Bogdanović, Milena Frtunić Gligorijević, Jelena Kocić et al.

Various areas of natural language processing (NLP) have greatly benefited from the development of large language models in recent years. This research addresses the challenge of developing efficient tokenizers for transformer-based domain-specific language models. Tokenization efficiency within transformer-based models is directly related to model efficiency, which motivated the research we present in this paper. Our goal in this research was to demonstrate that the appropriate selection of data used for tokenizer training has a significant impact on tokenizer performance. Subsequently, we will demonstrate that efficient tokenizers and models can be developed even if language resources are limited. To do so, we will present a domain-adapted large language model tokenizer developed for masked language modeling of the Serbian legal domain. In this paper, we will present a comparison of the tokenization performance for a domain-adapted tokenizer in version 2 of the SrBERTa language model we developed, against the performances of five other tokenizers belonging to state-of-the-art multilingual, Slavic or Serbian-specific models—XLM-RoBERTa (base-sized), BERTić, Jerteh-81, SrBERTa v1, NER4Legal_SRB. The comparison is performed using a test dataset consisting of 275,660 samples of legal texts written in the Cyrillic alphabet gathered from the Official Gazette of the Republic of Serbia. This dataset contains 197,134 distinct words, while the overall word count is 5,265,352. We will show that our tokenizer, trained upon a domain-adapted dataset, outperforms presented tokenizers by at least 4.5% ranging to 54.62%, regarding the number of tokens generated for the whole test dataset. In terms of tokenizer fertility, we will show that our tokenizer outperforms compared tokenizers by at least 6.39% ranging to 56.8%.

Mateus M. Tarozo, Arthur A. B. Pessa, Luciano Zunino et al.

Quantitative analysis of visual arts has recently expanded to encompass a more extensive array of artworks due to the availability of large-scale digitized art collections. Consistent with formal analyses by art historians, many of these studies highlight the significance of encoding spatial structures within artworks to enhance our understanding of visual arts. However, defining universally applicable, interpretable, and sufficiently simple units that capture the essence of paintings and their artistic styles remains challenging. Here we examine ordering patterns in pixel intensities within two-by-two partitions of images from nearly 140,000 paintings created over the past thousand years. These patterns, categorized into eleven types based on arguments of continuity and symmetry, are both universally applicable and detailed enough to correlate with low-level visual features of paintings. We uncover a universal distribution of these patterns, with consistent prevalence within groups, yet modulated across groups by a nontrivial interplay between pattern smoothness and the likelihood of identical pixel intensities. This finding provides a standardized metric for comparing paintings and styles, further establishing a scale to measure deviations from the average prevalence. Our research also shows that these simple patterns carry valuable information for identifying painting styles, though styles generally exhibit considerable variability in the prevalence of ordinal patterns. Moreover, shifts in the prevalence of these patterns reveal a trend in which artworks increasingly diverge from the average incidence over time; however, this evolution is neither smooth nor uniform, with substantial variability in pattern prevalence, particularly after the 1930s.

Xindi Wang, Alexander J. Gates, Magnus Resch et al.

From disparities in the number of exhibiting artists to auction opportunities, there is evidence of women's under-representation in visual art. Here we explore the exhibition history and auction sales of 65,768 contemporary artists in 20,389 institutions, revealing gender differences in the artist population, exhibitions and auctions. We distinguish between two criteria for gender equity: gender-neutrality, when artists have gender-independent access to exhibition opportunities, and gender-balanced, that strives for gender parity in representation, finding that 58\% of institutions are gender-neutral but only 24\% are gender-balanced, and that the fraction of man-overrepresented institutions increases with institutional prestige. We define artist's co-exhibition gender to capture the gender inequality of the institutions that an artist exhibits. Finally, we use logistic regression to predict an artist's access to the auction market, finding that co-exhibition gender has a stronger correlation with success than the artist's gender. These results help unveil and quantify the institutional forces that relate to the persistent gender imbalance in the art world.

Shuai Wang, Ivona Najdenkoska, Hongyi Zhu et al.

Understanding visual art requires reasoning across multiple perspectives -- cultural, historical, and stylistic -- beyond mere object recognition. While recent multimodal large language models (MLLMs) perform well on general image captioning, they often fail to capture the nuanced interpretations that fine art demands. We propose ArtRAG, a novel, training-free framework that combines structured knowledge with retrieval-augmented generation (RAG) for multi-perspective artwork explanation. ArtRAG automatically constructs an Art Context Knowledge Graph (ACKG) from domain-specific textual sources, organizing entities such as artists, movements, themes, and historical events into a rich, interpretable graph. At inference time, a multi-granular structured retriever selects semantically and topologically relevant subgraphs to guide generation. This enables MLLMs to produce contextually grounded, culturally informed art descriptions. Experiments on the SemArt and Artpedia datasets show that ArtRAG outperforms several heavily trained baselines. Human evaluations further confirm that ArtRAG generates coherent, insightful, and culturally enriched interpretations.

Benoit Baudry, Erik Natanael Gustafsson, Roni Kaufman et al.

New media art builds on top of rich software stacks. Blending multiple media such as code, light or sound , new media artists integrate various types of software to draw, animate, control or synchronize different parts of an artwork. Yet, the artworks rarely credit software and all the developers involved. In this work, we present Myriad People, an original dataset of open source projects and their contributors, which span various software layers used in new media art installations. To collect this dataset, we released an open call for artists and eventually curated 9 artworks, which use a variety of software and media. In October 2024, we organized a collective exhibition in Stockholm, entitled Myriad, which showcased the 9 artworks. The Myriad People dataset includes the 124 open source projects used in one or more of the Myriad's artworks, as well as all the contributors to these projects. In this paper, we present the dataset, as well as the possible usages of this dataset for software and art research.