The ability to connect visual patterns with the processes that form them represents one of the deepest forms of visual understanding. Textures of clouds and waves, the growth of cities and forests, or the formation of materials and landscapes are all examples of patterns emerging from underlying mechanisms. We present the SciTextures dataset, a large-scale collection of textures and visual patterns from all domains of science, tech, and art, along with the models and code that generate these images. Covering over 1,270 different models and 100,000 images of patterns and textures from physics, chemistry, biology, sociology, technology, mathematics, and art, this dataset offers a way to explore the deep connection between the visual patterns that shape our world and the mechanisms that produce them. Built through an agentic AI pipeline that autonomously collects, implements, and standardizes scientific and generative models. This AI pipeline is also used to autonomously invent and implement novel methods for generating visual patterns and textures. SciTextures enables systematic evaluation of vision language models (VLM's) ability to link visual patterns to the models and code that generate them, and to identify different patterns that emerge from the same underlying process. We also test VLMs ability to infer and recreate the mechanisms behind visual patterns by providing a natural image of a real-world phenomenon and asking the AI to identify and code a model of the process that formed it, then run this code to generate a simulated image that is compared to the reference image. These benchmarks reveal that VLM's can understand and simulate physical systems beyond visual patterns at multiple levels of abstraction. The dataset and code are available at: https://zenodo.org/records/17485502
Subjective interpretation and content diversity make predicting whether an image is private or public a challenging task. Graph neural networks combined with convolutional neural networks (CNNs), which consist of 14,000 to 500 millions parameters, generate features for visual entities (e.g., scene and object types) and identify the entities that contribute to the decision. In this paper, we show that using a simpler combination of transfer learning and a CNN to relate privacy with scene types optimises only 732 parameters while achieving comparable performance to that of graph-based methods. On the contrary, end-to-end training of graph-based methods can mask the contribution of individual components to the classification performance. Furthermore, we show that a high-dimensional feature vector, extracted with CNNs for each visual entity, is unnecessary and complexifies the model. The graph component has also negligible impact on performance, which is driven by fine-tuning the CNN to optimise image features for privacy nodes.
Thompson Sampling (TS) and its variants are powerful Multi-Armed Bandit algorithms used to balance exploration and exploitation strategies in active learning. Yet, their probabilistic nature often turns them into a "black box", hindering debugging and trust. We introduce TS-Insight, a visual analytics tool explicitly designed to shed light on the internal decision mechanisms of Thompson Sampling-based algorithms, for model developers. It comprises multiple plots, tracing for each arm the evolving posteriors, evidence counts, and sampling outcomes, enabling the verification, diagnosis, and explainability of exploration/exploitation dynamics. This tool aims at fostering trust and facilitating effective debugging and deployment in complex binary decision-making scenarios especially in sensitive domains requiring interpretable decision-making.
In this paper, we propose AUREXA-SE (Audio-Visual Unified Representation Exchange Architecture with Cross-Attention and Squeezeformer for Speech Enhancement), a progressive bimodal framework tailored for audio-visual speech enhancement (AVSE). AUREXA-SE jointly leverages raw audio waveforms and visual cues by employing a U-Net-based 1D convolutional encoder for audio and a Swin Transformer V2 for efficient and expressive visual feature extraction. Central to the architecture is a novel bidirectional cross-attention mechanism, which facilitates deep contextual fusion between modalities, enabling rich and complementary representation learning. To capture temporal dependencies within the fused embeddings, a stack of lightweight Squeezeformer blocks combining convolutional and attention modules is introduced. The enhanced embeddings are then decoded via a U-Net-style decoder for direct waveform reconstruction, ensuring perceptually consistent and intelligible speech output. Experimental evaluations demonstrate the effectiveness of AUREXA-SE, achieving significant performance improvements over noisy baselines, with STOI of 0.516, PESQ of 1.323, and SI-SDR of -4.322 dB. The source code of AUREXA-SE is available at https://github.com/mtanveer1/AVSEC-4-Challenge-2025.
It is widely accepted that visual representations are iconic and differ from the symbolic representations of propositional attitudes. Iconic representations compose differently from symbolic representations. Symbolic compositionality is canonical (it conforms to a set of rules determined by symbolic logic or by some grammar). Iconic representations display a whole/parts compositionality, in the way parts of objects combine to form whole objects. In this paper, I take recourse to Mereotopology as it applies to the compositionality of parts to form wholes to explain, first, the compositionality of icons, and to argue, second, that the hardwiring of our visual system is such as to reflect the basic compositional rules of Mereotopology.
Numerical computations of stellar oscillations for models representative of B-type stars predict fewer modes to be excited than observations reveal from modern space-based photometric data. One shortcoming of state-of-the-art evolution models of B-type stars that may cause a lack of excited modes is the absence of microscopic diffusion in most such models. We investigate whether the inclusion of microscopic diffusion in stellar models of B-type stars, notably radiative levitation experienced by isotopes, leads to extra mode driving by the opacity mechanism compared to the case of models that do not include microscopic diffusion. We consider the case of slowly to moderately rotating stars and use non-rotating equilibrium models, while we account for (uniform) rotation in the computations of the pulsation frequencies. We calculate 1D stellar models with and without microscopic diffusion and examine the effect of radiative levitation on mode excitation, for both low-radial order pressure and gravity modes and for high-radial order gravity modes. We find systematically more modes to be excited for the stellar models including microscopic diffusion compared to those without it, in agreement with observational findings of pulsating B-type dwarfs. Furthermore, the models with microscopic diffusion predict that excited modes occur earlier on in the evolution compared to modes without it. In order to maintain realistic surface abundances during the main sequence, we include macroscopic envelope mixing by internal gravity waves. While radiative levitation has so far largely been neglected in stellar evolution computations of B-type stars for computational convenience, it impacts mode excitation predictions for stellar models of such stars. We conclude that the process of radiative levitation is able to reduce the discrepancy between predicted and observed excited pulsation modes in B-type stars.
Automated software testing is integral to the software development process, streamlining workflows and ensuring product reliability. Visual testing, particularly for user interface (UI) and user experience (UX) validation, plays a vital role in maintaining software quality. However, conventional techniques such as pixel-wise comparison and region-based visual change detection often fail to capture contextual similarities, subtle variations, and spatial relationships between UI elements. In this paper, we propose a novel graph-based approach for context-aware visual change detection in software test automation. Our method leverages a machine learning model (YOLOv5) to detect UI controls from software screenshots and constructs a graph that models their contextual and spatial relationships. This graph structure is then used to identify correspondences between UI elements across software versions and to detect meaningful changes. The proposed method incorporates a recursive similarity computation that combines structural, visual, and textual cues, offering a robust and holistic model of UI changes. We evaluate our approach on a curated dataset of real-world software screenshots and demonstrate that it reliably detects both simple and complex UI changes. Our method significantly outperforms pixel-wise and region-based baselines, especially in scenarios requiring contextual understanding. We also discuss current limitations related to dataset diversity, baseline complexity, and model generalization, and outline planned future improvements. Overall, our work advances the state of the art in visual change detection and provides a practical solution for enhancing the reliability and maintainability of evolving software interfaces.
Diederik Aerts, Jonito Aerts Arguëlles, Lester Beltran
et al.
Einstein's article on the EPR paradox is the most cited of his works, but not many know that it was not fully representative of the way he thought about the incompleteness of the quantum formalism. Indeed, his main worry was not Heisenberg's uncertainty principle, which he accepted, but the experimental non-separability of spatially separate systems. The same problem was also recognized, years later, by one of us, as part of an axiomatic analysis of the quantum formalism, which revealed an unexpected structural limitation of the quantum formalism in Hilbert space, preventing the description of separate systems. As we will explain, this limitation does not manifest at the level of the states, but of the projectors describing the properties, in the sense that there are not enough properties in the formalism to describe separate systems. The question remains whether separability is a possibility at the fundamental level and if a formalism should integrate it into its mathematical structure, as a possibility. To aid our intuition, we offer a reflection based on a powerful analogy between physical systems and human conceptual entities, as the question of separability also arises for the latter.
Since the emergence of digital media in the 1990s, a new realm of interaction between the visual arts and religion has been forged and evolved. The spread of visual media technologies has significantly influenced the study of religious visual art worldwide after the 1990s. Despite this, the field of religious visual art during the digital era is still relatively uncharted, with a notable absence of comprehensive theoretical frameworks. To address this gap, the present paper employs bibliometric methods, conducting a thorough review and analysis of 2544 pieces of international academic literature in the domain of religion and visual arts post-1990s. The analytical framework is structured into three primary sections, each dedicated to answering key questions: (1) what constitutes the inherent relationship in the study of religion and visual art?, (2) what disciplinary context do these interplays occur within?, and (3) in which domains and regions does this interplay predominantly unfold? The outcomes of this rigorous analysis offer valuable insights into interdisciplinary influences and evolving research trends within the realm of religious visual art. These findings stand to benefit art researchers and practitioners, providing a comprehensive overview of potential avenues for the exploration of visual arts with religious themes. Through a systematic investigation, this research endeavors to heighten scholars’ awareness of the significance of visual arts in the field of religion and illuminate the interdisciplinary trends at the intersection of religion and visual arts.
Danielle Abrams’s performance art critically engages with late twentieth-century debates on race, queerness, and identity, positioning her as a vital figure in challenging monolithic and heteronormative structures of identity. Her early work Quadroon (1998), a live performance and four-channel video installation blending music, costume, gesture, and speech, compounds impassioned debates within the art world and beyond around the impact of multiculturalism on identity-based art, the invisibility of Jews of color and other marginalized members of the Jewish community, and the state of Black/Jewish relations in the United States following the Crown Heights riots of 1991. Abrams’s pieces frequently negotiate the tensions and intersections between her Black and Jewish familial heritage and her lesbian identity through the embodiment of semi-fictional personae grounded in family lore, self-perceptions, and cultural stereotypes. This paper explores how Abrams destabilizes the readability of “authentic” identities on the surface of the body in Quadroon via her adoption of personifications of her Black grandmother, her Jewish great grandmother, her identification as a butch lesbian, and her (unsuccessful) teenage attempt at passing for Greek. Pairing video recordings of each character with interludes from an unpublished performance script, I consider the anxieties of passing expressed in the personas of Dew Drop and Janie Bell, and through the lens of Abrams’s diaries, pose Butch in the Kitchen’s potential as an indefinite body to queer socially imposed constructions of monolithic and essentialist identity.
Artwork recommendation is challenging because it requires understanding how users interact with highly subjective content, the complexity of the concepts embedded within the artwork, and the emotional and cognitive reflections they may trigger in users. In this paper, we focus on efficiently capturing the elements (i.e., latent semantic relationships) of visual art for personalized recommendation. We propose and study recommender systems based on textual and visual feature learning techniques, as well as their combinations. We then perform a small-scale and a large-scale user-centric evaluation of the quality of the recommendations. Our results indicate that textual features compare favourably with visual ones, whereas a fusion of both captures the most suitable hidden semantic relationships for artwork recommendation. Ultimately, this paper contributes to our understanding of how to deliver content that suitably matches the user's interests and how they are perceived.
This article explores how several 21st century narrative nonfiction and documentary artists resort to contemporary ruins to figure the Anthropocene. In order to deal with the relative invisibility and extreme complexity of the phenomenon, artists and writers often borrow from the ruins of other catastrophes. With an hallucinatory superimposition, they project contemporary ecological disaster onto existing ruins, and in doing so, they rely on the power of the atomic imaginary or the ideological void which follows economic crises. This “catachronism” (Srinivas Aravamudan, 2013) chosen by some contemporary artists and writers prevents us from understanding global warming, because it aestheticizes the Anthropocene as a mesmerizing post-apocalyptic time. What are the alternative uses of contemporary ruins for artists and writers who have decided to distance themselves from any melancholic fascination? Through a few examples (writers Anna Lowenhaupt Tsing, William T. Volmann, Sylvain Tesson, but also French videoartist Pierre Huyghe), we will explore the tension which emerges between the aestheticization and the mobilization of ruins.
Bu araştırmada, Deneysel Sanat Atölyesi dersinde, farklı sanat disiplinlerinde öğrenimini tamamlamış öğrencilerin (lisansüstü) Anadolu Kültürü’nün önemli figürlerinden biri olan Yunus Emre’nin evrensel fikirlerini görsel sanatların diliyle nasıl yorumladığını ortaya koymak amaçlanmıştır. Bu amaç doğrultusunda yerel içerikten hareketle sanatsal üretim sürecinin nasıl gerçekleştiği, farklı disiplinlerde çalışan katılımcıların görsel ifade sürecinde nasıl etkileşim kurduğu, alanına özgü araç, gereç ve malzemenin nasıl kullanıldığı ve yerel içeriğin farklı disiplinlerin etkileşimi konusunda rolünün ne olduğu sorularına yanıt aranmıştır. Nitel araştırmanın durum çalışması deseni ile yürütülen araştırma derslere davet edilen 5 konuk sanatçı ve 12 öğrencinin katılımıyla gerçekleştirilmiştir. Araştırmada gözlem, yarı yapılandırılmış görüşme, araştırmacı ve katılımcı günlükleri, katılımcı çalışmaları ve ders video kayıtlarıyla toplanan veriler tümevarımsal analiz ile çözümlenmiştir. Araştırmada katılımcıların uygulama sürecinde kendi alanlarından yola çıktıkları, temayı deneyimleriyle ilişkilendirerek deneysel araştırmalarla çalıştıkları diğer yandan da deneysel çalışmayı simge kullanımına ve malzemeye indirgedikleri ortaya çıkmıştır. Katılımcıların uygulama sürecinde kendi alanının kalıplarının dışına çıkmakta zorlandıkları görülmüştür. Yeni bir şey söyleme, yeni olanı arama çabasının, katılımcıları estetik sorgulamaya yönlendirdiği, diğer yandan da bu durumun onların uygulamaya başlamalarını zorlaştırdığı ortaya çıkmıştır. Araştırmada disiplinlerarası bir içerikle katılımcıların malzeme ve teknik kullanımında denemelere olanak tanınması sonucunda farklı perspektifler geliştirmeye katkı sağlandığı söylenebilir. Ayrıca araştırmanın çeşitli sanatçı ve sanat yapımlarıyla karşılaşmalar yaratarak katılımcıları sanatın anlamı üzerine yeniden düşünme, estetik değeri sorgulama, sanat tarihi bilgisini sınama gibi konular üzerinde düşünmeye ve araştırmaya davet ettiği söylenebilir.
Education (General), Theory and practice of education
The exhibition Arte Programmata. Arte cinetica, opere moltiplicate, opera aperta (Programmed Art. Kinetic Art, Multiplied Works, Open Work), opened in May 1962 at the Olivetti store in Milan. The event, organized by Bruno Munari and Giorgio Soavi and presented by Umberto Eco, represents an early reflection on the use of technology applied to art at the beginning of this intersection. Participants include Group T and Group N as well as Enzo Mari and Munari himself. The essay intends to situate the exhibition in the historical moment that marks the origins of the electronic culture in Italy, showing how the development of technology influenced the artistic research. Olivetti company plays a prominent role in addressing both artists and curators towards the most innovative experiences that were developing in the field of electronics; the company's interdisciplinary approach, which was able to generate a specificity of design and vision unique in the international scene, is also highlighted. The article aims to investigate the Italian origins of the phenomenon and the effect of electronic culture on the visual arts as part of a broader dialogue between art, design, industry, and innovation.
‘Visual Music’ has a long history, much longer than most people realize. Over time, several eminent scientists, musicians, and artists have tried to establish correspondences between sound and vision. Some of these efforts were based on scientific principles, some on genuine synesthetic experiences, while others were more obviously creative aesthetic choices. With the resurgence of interest in this field, the argument presented here is that now is the time to re-evaluate this canon of knowledge, to identify more clearly, and expand the core concepts at its center. A selection of works, by pioneering film makers from the twentieth century, are examined from a semiotically informed perspective, to reevaluate some of the history of Visual Music alongside new ideas from the adjacent fields of science, psychology, and neuroscience. To this end a range of principles/parameters are outlined that arguably constitute the fundamentals of all creative approaches that translate between sound and vision going forward.
Fine arts education, a term widely used to define the school subject, is no longer appropriate to describe artistic expression goals in the educational context. Contemporary visual education allows for a comprehensive approach that considers the intermediality of contemporary visual art. Pedagogical methods, processes, and goals should be open to different approaches under the teacher’s guide. This paper presents reflections on the pedagogical process and a concrete example of a performance developed by secondary school students. It refers to an intermedial project that allows discussing multisensory perception, interdisciplinarity, and the integration of different fields of study, showing an intermedial approach to the pedagogical process. The example shows how creativity develops and grows with such an approach.
Recently, virtual reality (VR) technology has been widely used in medical, military, manufacturing, entertainment, and other fields. These applications must simulate different complex material surfaces, various dynamic objects, and complex physical phenomena, increasing the complexity of VR scenes. Current computing devices cannot efficiently render these complex scenes in real time, and delayed rendering makes the content observed by the user inconsistent with the user's interaction, causing discomfort. Foveated rendering is a promising technique that can accelerate rendering. It takes advantage of human eyes' inherent features and renders different regions with different qualities without sacrificing perceived visual quality. Foveated rendering research has a history of 31 years and is mainly focused on solving the following three problems. The first is to apply perceptual models of the human visual system into foveated rendering. The second is to render the image with different qualities according to foveation principles. The third is to integrate foveated rendering into existing rendering paradigms to improve rendering performance. In this survey, we review foveated rendering research from 1990 to 2021. We first revisit the visual perceptual models related to foveated rendering. Subsequently, we propose a new foveated rendering taxonomy and then classify and review the research on this basis. Finally, we discuss potential opportunities and open questions in the foveated rendering field. We anticipate that this survey will provide new researchers with a high-level overview of the state of the art in this field, furnish experts with up-to-date information and offer ideas alongside a framework to VR display software and hardware designers and engineers.
For two decades, the formalism of quantum mechanics has been successfully used to describe human decision processes, situations of heuristic reasoning, and the contextuality of concepts and their combinations. The phenomenon of 'categorical perception' has put us on track to find a possible deeper cause of the presence of this quantum structure in human cognition. Thus, we show that in an archetype of human perception consisting of the reconciliation of a bottom up stimulus with a top down cognitive expectation pattern, there arises the typical warping of categorical perception, where groups of stimuli clump together to form quanta, which move away from each other and lead to a discretization of a dimension. The individual concepts, which are these quanta, can be modeled by a quantum prototype theory with the square of the absolute value of a corresponding Schrödinger wave function as the fuzzy prototype structure, and the superposition of two such wave functions accounts for the interference pattern that occurs when these concepts are combined. Using a simple quantum measurement model, we analyze this archetype of human perception, provide an overview of the experimental evidence base for categorical perception with the phenomenon of warping leading to quantization, and illustrate our analyses with two examples worked out in detail.
Diederik Aerts, Jonito Aerts Arguëlles, Lester Beltran
et al.
Inspired by foundational studies in classical and quantum physics, and by information retrieval studies in quantum information theory, we prove that the notions of 'energy' and 'entropy' can be consistently introduced in human language and, more generally, in human culture. More explicitly, if energy is attributed to words according to their frequency of appearance in a text, then the ensuing energy levels are distributed non-classically, namely, they obey Bose-Einstein, rather than Maxwell-Boltzmann, statistics, as a consequence of the genuinely 'quantum indistinguishability' of the words that appear in the text. Secondly, the 'quantum entanglement' due to the way meaning is carried by a text reduces the (von Neumann) entropy of the words that appear in the text, a behaviour which cannot be explained within classical (thermodynamic or information) entropy. We claim here that this 'quantum-type behaviour is valid in general in human language', namely, any text is conceptually more concrete than the words composing it, which entails that the entropy of the overall text decreases. In addition, we provide examples taken from cognition, where quantization of energy appears in categorical perception, and from culture, where entities collaborate, thus 'entangle', to decrease overall entropy. We use these findings to propose the development of a new 'non-classical thermodynamic theory' for human cognition, which also covers broad parts of human culture and its artefacts and bridges concepts with quantum physics entities.
È ormai noto come la produzione digitale abbia quasi del tutto soppiantato le tradizionali pratiche del disegno nel processo architettonico. Se da un lato l’uso della rappresentazione digitale ha interrotto la produzione grafica tradizionale, dall’altro essa rende possibile una sempre più efficace e immersiva disseminazione e divulgazione di progetti architettonici antichi non sufficientemente conosciuti, se non inediti o, ancora, immaginati. In questo senso, il presente contributo vuole indagare e sviluppare la digitalizzazione di uno dei più importanti progetti in ambito costiero posto in essere da parte del Ministero dei Lavori Pubblici e concretizzato mediante la redazione dell’Album dei fari illustrato dalle notizie intorno ai loro caratteri e posizione, al fine di rendere fruibili tutti quei progetti in tutto o in parte realizzati per la crescita delle nostre coste. Il progetto proposto nel 1873, all’indomani dell’Unità d’Italia, prevede la progettazione e la realizzazione di quattrocentosessantadue segnalamenti marittimi per gli ottomila chilometri di costa italiana. La digitalizzazione dell’Album dei fari, ovvero un caposaldo per la storia della costruzione di queste architetture costiere, si configura dunque come l’azione fondamentale per intraprendere un percorso di conoscenza e comparazione di tipo digitale delle strutture costiere passate e presenti, secondo i dettami dell’interdisciplinarietà [Albisinni, De Carlo 2011].