Hasil untuk "Visual arts"

Ulisses Razzante Vaccari

O presente artigo busca mostrar como as filosofias da arte de Peter Szondi e Peter Bürger retornam a Hegel em busca de um fundamento dialético para a historicização de conceitos estéticos da arte contemporânea. A dialética forma-conteúdo de Hegel permite a Szondi e Bürger compreender a evolução da arte contemporânea em prol da transformação da forma da arte em seu conteúdo sedimentado. Em Szondi tal transformação se evidencia historicamente a partir do drama moderno e se concretiza no teatro épico, enquanto em Bürger ela pode ser observada na arte vanguardista, a partir de sua crítica imanente à arte orgânica. Em seu final, o artigo esboça ainda algumas consequências dessa teoria para a crítica de arte brasileira, particularmente de Antonio Candido e Roberto Schwarz.

Slavica Srbinovska

Florian Zeller’s The Father is a film about dementia as a narrative disorder. The film tells a fragmented story through the eyes of Anthony, who is living with late-onset dementia. In it, the spectator is asked to witness Anthony’s encounters with his environment, which always result in a cognitive blankness—a lack of recognition that is the symptom of his condition. The film both represents and enacts this blankness by asking the spectator to witness and misunderstand a series of scenes strung together by nothing more than that lack of recognition. The Father thus constitutes not only a narrative of dementia but also a narrative about narrative—about its grammars, processes, and agents; about the questions of narratability and cognition attendant to any act of storytelling, and about how the answers to those questions might change when they are posed in the cinematic.

Viswa Chaitanya Marella, Sai Teja Erukude, Suhasnadh Reddy Veluru

The introduction of Artificial Intelligence (AI) into the domains of traditional art (visual arts, performing arts, and crafts) has sparked a complicated discussion about whether this might be an agent of disruption or an enhancement of our traditional art forms. This paper looks at the duality of AI, exploring the ways that recent technologies like Generative Adversarial Networks and Diffusion Models, and text-to-image generators are changing the fields of painting, sculpture, calligraphy, dance, music, and the arts of craft. Using examples and data, we illustrate the ways that AI can democratize creative expression, improve productivity, and preserve cultural heritage, while also examining the negative aspects, including: the threats to authenticity within art, ethical concerns around data, and issues including socio-economic factors such as job losses. While we argue for the context-dependence of the impact of AI (the potential for creative homogenization and the devaluation of human agency in artmaking), we also illustrate the potential for hybrid practices featuring AI in cuisine, etc. We advocate for the development of ethical guidelines, collaborative approaches, and inclusive technology development. In sum, we are articulating a vision of AI in which it amplifies our innate creativity while resisting the displacement of the cultural, nuanced, and emotional aspects of traditional art. The future will be determined by human choices about how to govern AI so that it becomes a mechanism for artistic evolution and not a substitute for the artist's soul.

Ishara Devendra, Chaman Wijesiriwardana, Prasad Wimalaratne

Software security visualization is an interdisciplinary field that combines the technical complexity of cybersecurity, including threat intelligence and compliance monitoring, with visual analytics, transforming complex security data into easily digestible visual formats. As software systems get more complex and the threat landscape evolves, traditional text-based and numerical methods for analyzing and interpreting security concerns become increasingly ineffective. The purpose of this paper is to systematically review existing research and create a comprehensive taxonomy of software security visualization techniques through literature, categorizing these techniques into four types: graph-based, notation-based, matrix-based, and metaphor-based visualization. This systematic review explores over 60 recent key research papers in software security visualization, highlighting its key issues, recent advancements, and prospective future research directions. From the comprehensive analysis, the two main areas were distinctly highlighted as extensive software development visualization, focusing on advanced methods for depicting software architecture: operational security visualization and cybersecurity visualization. The findings highlight the necessity for innovative visualization techniques that adapt to the evolving security landscape, with practical implications for enhancing threat detection, improving security response strategies, and guiding future research.

Hyunsik Chae, Seungwoo Yoon, Jaden Park et al.

Recent Vision-Language Models (VLMs) have demonstrated impressive multimodal comprehension and reasoning capabilities, yet they often struggle with trivially simple visual tasks. In this work, we focus on the domain of basic 2D Euclidean geometry and systematically categorize the fundamental, indivisible visual perception skills, which we refer to as atomic visual skills. We then introduce the Atomic Visual Skills Dataset (AVSD) for evaluating VLMs on the atomic visual skills. Using AVSD, we benchmark state-of-the-art VLMs and find that they struggle with these tasks, despite being trivial for adult humans. Our findings highlight the need for purpose-built datasets to train and evaluate VLMs on atomic, rather than composite, visual perception tasks.

Gene Tangtartharakul, Katherine R. Storrs

Visual Language Models (VLMs) show remarkable performance in visual reasoning tasks, successfully tackling college-level challenges that require high-level understanding of images. However, some recent reports of VLMs struggling to reason about elemental visual concepts like orientation, position, continuity, and occlusion suggest a potential gulf between human and VLM vision. Here we use the toolkit of neuropsychology to systematically assess the capabilities of three state-of-the-art VLMs across visual domains. Using 51 tests drawn from six clinical and experimental batteries, we characterise the visual abilities of leading VLMs relative to normative performance in healthy adults. While the models excel in straightforward object recognition tasks, we find widespread deficits in low- and mid-level visual abilities that would be considered clinically significant in humans. These selective deficits, profiled through validated test batteries, suggest that an artificial system can achieve complex object recognition without developing foundational visual concepts that in humans require no explicit training.

Jiahao Guo, Sinan Du, Jingfeng Yao et al.

Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations, optimized for multimodal understanding tasks, harbor an inherent potential for visual generation. In this paper, we propose VGT, Visual Generation Tuning, a novel paradigm designed to stimulate the underlying capabilities of visual generation within any vision language models. By performing efficient visual generation tuning on well-pretrained VLMs, we significantly mitigate the alignment costs and accelerate the convergence of autoregressive modeling in the continuous space (20x speedup). Specifically, we dismiss the entangled pixel-level VAEs designed for diffusion transformers and formulate VGT-AE through aligning the semantic encoders from pretrained VLMs with the latent representations of pixel decoders. In image reconstruction tasks, we achieve 26.67 PSNR and 0.50 rFID at a 28x compression ratio, outperforming specialized VAEs; in visual generation tasks, we achieve state-of-the-art outcomes among autoregressive models, 0.77 on GenEval and 78.73 on DPG-Bench. Furthermore, our proposed VGT showcases significant scaling promise and is versatile for endowing any VLMs trained for multimodal understanding with the capabilities of visual generation, which paves the new avenue to explore next-generation unified multimodal foundation models. Models and codes are available at https://github.com/hustvl/VGT.

Maurizio Forte

This research is part of the NeuroArtIfAct project []aimed at exploring the cognitive and emotional processes involved in perceiving Etruscan artifacts. This case study is focused on the Sarcophagus of the Spouses at the National Etruscan Museum in Rome. The study utilized AI and eye-tracking technology to analyze how viewers engage with the Etruscan Sarcophagus of the Spouses, revealing key patterns of visual attention and engagement. Open AI ChatGBT 4o was used in conjunction with Python in order to elaborate all the spreadsheets and data coming from the eye0tracking recording. Results showed that viewers primarily focused on the central figures, especially the faces and hands, indicating a high level of interest in the human elements of the artifact. The longer fixation durations on these features suggest that viewers find them particularly engaging, likely due to their detailed craftsmanship and symbolic significance. The eye-tracking data also highlighted specific gaze patterns, such as diagonal scanning across the sarcophagus, which reflects the composition's ability to guide viewer attention strategically. These findings suggest that the artifact's design effectively captures and directs viewer attention, emphasizing its cultural and emotional significance.

Eva Maria Kuehn

The potential of Non-Fungible Tokens (NFTs) is highly anticipated, particularly in the realm of visual arts. However, current applications within fine arts often involve trivial processes, such as creating digital versions of artworks or replicas of masterpieces as NFT images, and selling only these NFTs. To unlock the full potential of NFTs, more innovative models are needed. This paper introduces a novel model that establishes a permanent link between an NFT and a physical craft object. This linkage is utilized to orchestrate the trade workflow, ensuring a sustained connection between real and digital artifacts. A distinguishing feature is that they can be sold together or seperately and later reunited with a buyer. The NFT serves as a multifunctional certificate, tracing, and communication token.Through a comprehensive analysis, this paper explores diverse scenarios that may arise in the relationship between the physical object and its digital twin. It presents a systematic and formal description of the proposed model and its various cases, marking a pioneering effort in the field. Noteworthy advantages include the ability to detect plagiarism and fraud. By strategically incorporating stakeholder roles, the model preserves the anonymity of art collectors while extracting valuable information about the ownership of physical artworks. The primary objective is to enhance security in the art trade and foster new business opportunities for stakeholders. As a proof-of-concept, the model was implemented in a real-world scenario on a leading NFT marketplace platform.

Rodrigo Martínez-Rodríguez, Paula Fernández-Gago

El presente artículo explora el fenómeno del consumo identitario y la importancia de considerar, en el diseño de producto, las distintas posibilidades de inclusión de valores de distinta índole. Se aleja de una visión exclusiva del diseño como una disciplina configuradora con base en el binomio forma-función. Este trabajo expone la relevancia de dotar de identidad a los productos y, con ello, la posibilidad de creación de significados, al profundizar en la clasificación de valores de consumo- culturales, experienciales y racionales-. Esto se hace a través de ejemplos y casos prácticos que demuestran la importancia de emplear la identidad como un activo importante de consumo.

Levi Cai, Nathan E. McGuire, Roger Hanlon et al.

In-situ visual observations of marine organisms is crucial to developing behavioural understandings and their relations to their surrounding ecosystem. Typically, these observations are collected via divers, tags, and remotely-operated or human-piloted vehicles. Recently, however, autonomous underwater vehicles equipped with cameras and embedded computers with GPU capabilities are being developed for a variety of applications, and in particular, can be used to supplement these existing data collection mechanisms where human operation or tags are more difficult. Existing approaches have focused on using fully-supervised tracking methods, but labelled data for many underwater species are severely lacking. Semi-supervised trackers may offer alternative tracking solutions because they require less data than fully-supervised counterparts. However, because there are not existing realistic underwater tracking datasets, the performance of semi-supervised tracking algorithms in the marine domain is not well understood. To better evaluate their performance and utility, in this paper we provide (1) a novel dataset specific to marine animals located at http://warp.whoi.edu/vmat/, (2) an evaluation of state-of-the-art semi-supervised algorithms in the context of underwater animal tracking, and (3) an evaluation of real-world performance through demonstrations using a semi-supervised algorithm on-board an autonomous underwater vehicle to track marine animals in the wild.

Leonardo Impett, Fabian Offert

In this paper, we revisit Johanna Drucker's question, "Is there a digital art history?" -- posed exactly a decade ago -- in the light of the emergence of large-scale, transformer-based vision models. While more traditional types of neural networks have long been part of digital art history, and digital humanities projects have recently begun to use transformer models, their epistemic implications and methodological affordances have not yet been systematically analyzed. We focus our analysis on two main aspects that, together, seem to suggest a coming paradigm shift towards a "digital" art history in Drucker's sense. On the one hand, the visual-cultural repertoire newly encoded in large-scale vision models has an outsized effect on digital art history. The inclusion of significant numbers of non-photographic images allows for the extraction and automation of different forms of visual logics. Large-scale vision models have "seen" large parts of the Western visual canon mediated by Net visual culture, and they continuously solidify and concretize this canon through their already widespread application in all aspects of digital life. On the other hand, based on two technical case studies of utilizing a contemporary large-scale visual model to investigate basic questions from the fields of art history and urbanism, we suggest that such systems require a new critical methodology that takes into account the epistemic entanglement of a model and its applications. This new methodology reads its corpora through a neural model's training data, and vice versa: the visual ideologies of research datasets and training datasets become entangled.

Sereno Innocenti

It is not so unusual to leaf through a book before reading it, without even being sure to do it later. The accomplished act that summarizes this operation, traditionally considered an instinctive and common belief to many, is often depicted in the iconic paintings concerning the Annunciation of the Madonna. The Annunciation to the Virgin Mary is, in fact, one of the most represented themes in the history of art, and the three characters (Angel, Virgin, and the dove) involved in their meanings and signifiers, always interact within an architectural scene, in which the only accessory present is (almost always) a book. The pose of Our Lady towards this object is, in most cases, that of a pause or a rest, and here the doubt arises: if surprised by the event, she is interrupting the reading, or she is simply leafing through that book. [read more]

Laila Thaíse Batista de Oliveira, Luciana Oliveira Vieira, Naira Évine Pereira Soares

O artigo realiza um levantamento das mostras e festivais de cinema negro na região Nordeste e analisa os modos de organização dessas equipes como espaços de aquilombamentos, preservando locais de encontro e (re)existência do cinema negro, articulando essa discussão ao pensamento de Beatriz Nascimento sobre o conceito de quilombo como resistência cultural. Neste sentido, fazemos também uma breve reflexão histórica sobre a construção social do Nordeste, apresentando um estudo inicial sobre as estratégias de sobrevivência que esses eventos negros vêm desenvolvendo diante da ausência histórica de investimento público cultural na região. Nessa pesquisa inicial foi possível analisar dados relacionados a gênero e raça nas lideranças desses eventos, período de surgimento, modos de financiamento e estados onde estão localizados. Em pouco mais de 7 anos a região Nordeste já conta com 9 mostras e festivais de cinema negro, representando assim um importante cenário para este cinema no Brasil.

Andrea Reisenauer

A growing body of research has been devoted to examining the parallels between translation and film adaptation. Given these parallels and the role of translation in intercultural exchange, this paper aims to explore the role of film adaptation as another possible means of exchange, i.e. how literature crosses borders through film adaptations. To do so, it will draw upon the case of Spanish literary works (i.e., from the nation of Spain) that have been present in the United States as both film adaptations and literary translations. This will be done by analyzing a corpus of Spanish films that have been imported into the United States as both film adaptations and literary translations between the years 1895 and 2018. Theoretical tools from the Polysystem theory will be used to examine the characteristics of these films, their corresponding literary works, and the combinations arising from their importation. Seven main patterns governing the relationship between film adaptation and literary translation will be revealed and briefly illustrated.

Tao Yang, Yuwang Wang, Yan Lu et al.

Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fields such as disentangled representation learning and scene decomposition. Towards this goal, we propose an unsupervised transformer-based Visual Concepts Tokenization framework, dubbed VCT, to perceive an image into a set of disentangled visual concept tokens, with each concept token responding to one type of independent visual concept. Particularly, to obtain these concept tokens, we only use cross-attention to extract visual information from the image tokens layer by layer without self-attention between concept tokens, preventing information leakage across concept tokens. We further propose a Concept Disentangling Loss to facilitate that different concept tokens represent independent visual concepts. The cross-attention and disentangling loss play the role of induction and mutual exclusion for the concept tokens, respectively. Extensive experiments on several popular datasets verify the effectiveness of VCT on the tasks of disentangled representation learning and scene decomposition. VCT achieves the state of the art results by a large margin.

Stepan Vaneyan / Степан Сережьевич Ванеян

Max Imdahl is situated on the border between the theory and practice of visual arts. His life is an experience of combining academic art history with cutting-edge art criticism. His ‘ikonik’ was intended as a continuation and completion of the methodological development of art history from iconography to iconology. Instead of the hermeneutics of the immanent meaning of an artwork, the semantics of an act of vision becomes the object of his interpretation, and criticism of cognitive capacities of language as a means of articulating artistic experience becomes his purpose. Imdahl juxtaposes his ‘ikonik’ as a theologised variant of receptive aesthetics with Hans Sedlmayr’s structural analysis. For Imdahl, Sedlmayr falls under suspicion for his all too static picture of the semantic element of an artwork, which, according to Sedlmayr, is divided into layers of meaning, unified by a single irrational (“endothymic”) basis. By contrast, ‘ikonik’ refers to the semantics emerging as simultaneous affects of the act of vision, which embraces dynamic oppositions of meaning, having a scenographic and choreographic character. Thus, the interaction with an artwork is equated to a performative act, which ensures the apophatic growth of meaning and the approach to the Revelation. The tropological decomposition of the structures of the contemplative mind (Sedlmayr) is continued by the eschatological deconstruction of the verbal discourse in the form of art history (Imdahl). Макс Имдаль располагается на границе между теорией и практикой визуальных искусств. Его жизненный путь – это опыт совмещения академической истории искусства и актуальной художественной критики. Его иконика задумывалась как продолжение и завершение методологического развития искусствознания от иконографии к иконологии. Вместо герменевтики имманентного произведению смысла объектом толкования становится семантика акта зрения, а целью – критика когнитивных возможностей языка как средства артикуляции творческого опыта. Свою иконику как теологизированный (с помощью неотомизма) вариант рецептивной эстетики Имдаль противопоставляет структурному анализу Зедльмайра, подозревая последнего в слишком статичной картине семантического устройства художественного произведения, якобы разделённого на смысловые слои, объединённые единым иррациональным («эндотимическим») основанием. Иконике же подвластны смыслы, возникающие как симультанные аффекты акта зрения, охватывающего динамически взаимодействующие смысловые противоположности сценографически-хореографического свойства. Тем самым взаимодействие с произведением искусства приравнивается к перформативному акту, что обеспечивает апофатический прирост смысла и приближение к собственно Откровению. Тропологическая декомпозиция структур созерцающего сознания (Зедльмайр) продолжается эсхатологической де-конструкцией самого вербального дискурса, имеющего вид истории искусства (Имдаль).

نوید جامعی, محمدرضا شریف زاده, سید مصطفی مختاباد امرئی et al.

ژولیا کریستوا با تبیین عملکرد امر نشانه‌ای و امر نمادین، حرکت توأمان این دو را برای بیان زبان هنر تشریح می‌کند. او با طرح سوبژکتیویته به عنوان عنصری که فرهنگ، تاریخ و زبان بر او تأثیر می‌گذارند، ساختار سوژه‌ی‌ در فرآیند را شرح داده و آن‌را در هنر مستقر می‌نماید. هنر از منظر او تخلیه‌ی انرژی‌های رانه‌ای در زبان است که ژوئیسانس خلق را در روبنای نمادین بکار می‌گیرد تا تجلی یابد. از این‌رو، آن‌چه به مدد تأثر سبب خلق اثر هنری می‌شود، می‌تواند معانیِ چندگانه را در پی داشته باشد و در این ساختارِ دو وجهی، بیننده در سویی دیگر ایستاده تا دست به تفسیر بزند. سوژه‌ی نگرنده به روند تولیدگری معنا وارد و عملکرد او منجر به ایجاد تفسیرهای متعدد می‌شود. آن‌چه از زیست عاطفیِ انسان بواسطه‌ی چیرگیِ گفتمان مسلط ستانده شده، توسط هنر بازتاب می‌یابد و این امر در عملکردهای نشانه‌ای به جهت تخطی از امر نمادین جریان یافته و تفسیرهای متعدد سوژه‌ی نگرنده از اثر به مثابه امری بازسازی‌کننده، حیات حسیِ انسان را احیاء می‌کند. این پژوهش با روش توصیفی-تحلیلی، با در نظر گرفتن مکانیزم تخطی‌گرایانه‌ی امر نشانه‌ای که مدام از امر نمادین سرپیچی می‌کند، نیروی هنر را در بازسازی و احیاء سوژه مورد واکاوی قرار داده و آثار هنرمندان پیشرو در دهه نود ایران را از این منظر، تحلیل خواهیم کرد و امکان همسوییِ ایده‌ی هنرمندان دهه نود ایران، از سنین و اقلیم‌های مختلف در وجود کرداری دال بر تمایل به تخطی از ساختار نمادین مورد سنجش قرار می‌گیرد.