Hasil untuk "Art"

Yilie Huang, Wenpin Tang, Xunyu Zhou

We consider time discretization for score-based diffusion models to generate samples from a learned reverse-time dynamic on a finite grid. Uniform and hand-crafted grids can be suboptimal given a budget on the number of time steps. We introduce Adaptive Reparameterized Time (ART) that controls the clock speed of a reparameterized time variable, leading to a time change and uneven timesteps along the sampling trajectory while preserving the terminal time. The objective is to minimize the aggregate error arising from the discretized Euler scheme. We derive a randomized control companion, ART-RL, and formulate time change as a continuous-time reinforcement learning (RL) problem with Gaussian policies. We then prove that solving ART-RL recovers the optimal ART schedule, which in turn enables practical actor--critic updates to learn the latter in a data-driven way. Empirically, based on the official EDM pipeline, ART-RL improves Fréchet Inception Distance on CIFAR-10 over a wide range of budgets and transfers to AFHQv2, FFHQ, and ImageNet without the need of retraining.

Florentin Koch

This article introduces Recursivism as a conceptual framework for analyzing contemporary artistic practices in the age of artificial intelligence. While recursion is precisely defined in mathematics and computer science, it has not previously been formalized as an aesthetic paradigm. Recursivism designates practices in which not only outputs vary over time, but in which the generative process itself becomes capable of reflexive modification through its own effects. The paper develops a five-level analytical scale distinguishing simple iteration, cumulative iteration, parametric recursion, reflexive recursion, and meta-recursion. This scale clarifies the threshold at which a system shifts from variation within a fixed rule to genuine self-modification of the rule itself. From this perspective, art history is reinterpreted as a recursive dynamic alternating between internal recursion within movements and meta-recursive transformations of their generative principles. Artificial intelligence renders this logic technically explicit through learning loops, parameter updates, and code-level self-modification. To distinguish Recursivism from related notions such as generative art, cybernetics, process art, and evolutionary art, the article proposes three operational criteria: state memory, rule evolvability, and reflexive visibility. These concepts are examined through case studies including Refik Anadol, Sougwen Chung, Karl Sims, and the Darwin-Godel Machine. The article concludes by examining the aesthetic, curatorial, and ethical implications of self-modifying artistic systems.

Thor Catteau, Benjamin Glancy, Allen Holder et al.

The central path revolutionized the study of optimization in the 1980s and 1990s due to its favorable convergence properties, and as such, it has been investigated analytically, algorithmically, and computationally. Past pursuits have primarily focused on linking iterative approximation algorithms to the central path in the design of efficient algorithms to solve large, and sometimes novel, optimization problems. This algorithmic intent has meant that the central path has rarely been celebrated as an aesthetic entity in low dimensions, with the only meager exceptions being illustrative examples in textbooks. We undertake this low dimensional investigation and illustrate the artistic use of the central path to create aesthetic tilings and flower-like constructs in two and three dimensions, an endeavor that combines mathematical rigor and artistic sensibilities. The result is a fanciful and enticing collection of patterns that, beyond computer generated images, supports math-aesthetic designs for novelties and museum-quality pieces of art.

Xiaolong Cui, Haoyu Geng, Guanghui Wang et al.

We introduce ART, a distribution-free and model-agnostic framework for changepoint detection that provides finite-sample guarantees. ART transforms independent observations into real-valued scores via a symmetric function, ensuring exchangeability in the absence of changepoints. These scores are then ranked and aggregated to detect distributional changes. The resulting test offers exact Type-I error control, agnostic to specific distributional or model assumptions. Moreover, ART seamlessly extends to multi-scale settings, enabling robust multiple changepoint estimation and post-detection inference with finite-sample error rate control. By locally ranking the scores and performing aggregations across multiple prespecified intervals, ART identifies changepoint intervals and refines subsequent inference while maintaining its distribution-free and model-agnostic nature. This adaptability makes ART as a reliable and versatile tool for modern changepoint analysis, particularly in high-dimensional data contexts and applications leveraging machine learning methods.

Kun Li, Yingqian Wang, Qiang Ling et al.

Hyperspectral anomaly detection (HAD) is challenging especially when anomalies are presented in sub-pixel form.The spectral signatures of anomalies in mixed pixels are mixed with those of background, making anomalies difficult to be distinguished from background. Most existing methods detect sub-pixel targets in abundance space by spectral unmixing. However, since abundance feature extraction and anomaly detection are decoupled, the learned features are not well-suitable for the subsequent detection. Moreover, these methods neglect the negative effect of anomalies on spectral unmixing, which leads to degradation of detection performance. To tackle these problems, we propose a cascaded autoencoder (AE) unmixing network for HAD. First, based on anomalies have larger spectral reconstruction errors than background, a background estimation approach is proposed to alleviate the negative effect of anomalies on spectral unmixing. Second, a cascaded AE is designed to achieve spectral unmixing from the estimated background to simultaneously obtain the endmembers and abundance vectors. Third, a deep Gaussian mixture model is leveraged to estimate the density distributions of spectral features since anomalies usually lie in the low-density areas. In this way, spectral unmixing and detection are jointly optimized to construct a unified detection framework. Experimental results demonstrate that our method achieves superior detection performance to existing state-of-the-art HAD methods.

Nicholas Steel, Clarissa Maria Mercedes Bauer-Staeb, John A Ford et al.

Summary: Background: Decades of steady improvements in life expectancy in Europe slowed down from around 2011, well before the COVID-19 pandemic, for reasons which remain disputed. We aimed to assess how changes in risk factors and cause-specific death rates in different European countries related to changes in life expectancy in those countries before and during the COVID-19 pandemic. Methods: We used data and methods from the Global Burden of Diseases, Injuries, and Risk Factors Study 2021 to compare changes in life expectancy at birth, causes of death, and population exposure to risk factors in 16 European Economic Area countries (Austria, Belgium, Denmark, Finland, France, Germany, Greece, Iceland, Ireland, Italy, Luxembourg, the Netherlands, Norway, Portugal, Spain, and Sweden) and the four UK nations (England, Northern Ireland, Scotland, and Wales) for three time periods: 1990–2011, 2011–19, and 2019–21. Changes in life expectancy and causes of death were estimated with an established life expectancy cause-specific decomposition method, and compared with summary exposure values of risk factors for the major causes of death influencing life expectancy. Findings: All countries showed mean annual improvements in life expectancy in both 1990–2011 (overall mean 0·23 years [95% uncertainty interval [UI] 0·23 to 0·24]) and 2011–19 (overall mean 0·15 years [0·13 to 0·16]). The rate of improvement was lower in 2011–19 than in 1990–2011 in all countries except for Norway, where the mean annual increase in life expectancy rose from 0·21 years (95% UI 0·20 to 0·22) in 1990–2011 to 0·23 years (0·21 to 0·26) in 2011–19 (difference of 0·03 years). In other countries, the difference in mean annual improvement between these periods ranged from –0·01 years in Iceland (0·19 years [95% UI 0·16 to 0·21] vs 0·18 years [0·09 to 0·26]), to –0·18 years in England (0·25 years [0·24 to 0·25] vs 0·07 years [0·06 to 0·08]). In 2019–21, there was an overall decrease in mean annual life expectancy across all countries (overall mean –0·18 years [95% UI –0·22 to –0·13]), with all countries having an absolute fall in life expectancy except for Ireland, Iceland, Sweden, Norway, and Denmark, which showed marginal improvement in life expectancy, and Belgium, which showed no change in life expectancy. Across countries, the causes of death responsible for the largest improvements in life expectancy from 1990 to 2011 were cardiovascular diseases and neoplasms. Deaths from cardiovascular diseases were the primary driver of reductions in life expectancy improvements during 2011–19, and deaths from respiratory infections and other COVID-19 pandemic-related outcomes were responsible for the decreases in life expectancy during 2019–21. Deaths from cardiovascular diseases and neoplasms in 2019 were attributable to high systolic blood pressure, dietary risks, tobacco smoke, high LDL cholesterol, high BMI, occupational risks, high alcohol use, and other risks including low physical activity. Exposure to these major risk factors differed by country, with trends of increasing exposure to high BMI and decreasing exposure to tobacco smoke observed in all countries during 1990–2021. Interpretation: The countries that best maintained improvements in life expectancy after 2011 (Norway, Iceland, Belgium, Denmark, and Sweden) did so through better maintenance of reductions in mortality from cardiovascular diseases and neoplasms, underpinned by decreased exposures to major risks, possibly mitigated by government policies. The continued improvements in life expectancy in five countries during 2019–21 indicate that these countries were better prepared to withstand the COVID-19 pandemic. By contrast, countries with the greatest slowdown in life expectancy improvements after 2011 went on to have some of the largest decreases in life expectancy in 2019–21. These findings suggest that government policies that improve population health also build resilience to future shocks. Such policies include reducing population exposure to major upstream risks for cardiovascular diseases and neoplasms, such as harmful diets and low physical activity, tackling the commercial determinants of poor health, and ensuring access to affordable health services. Funding: Gates Foundation.

Вікторія Олександрівна Гіголаєва-Юрченко, Олена Юріївна Смирна, Лариса Віталіївна Давидович

У статті представлено комплексну характеристику ґендерних відмінностей у процесі навчання академічного вокалу, які розглядаються як суттєвий чинник формування індивідуалізованої педагогічної стратегії. На основі узагальнення власного практичного досвіду викладачами-вокалістами кафедри хорового диригування та академічного співу Харківської державної академії культури здійснено ґрунтовний аналіз анатомо-фізіологічних і психофізіологічних особливостей чоловічого й жіночого голосового апарату, що безпосередньо впливають на характер звукоутворення, розвиток регістрової структури, дихальну координацію та специфіку резонансної підтримки звуку. Авторами окреслено специфіку методичної роботи з представниками різної статі: зокрема, для жіночих голосів важливим є формування стійкої опори в нижньому регістрі, вирівнювання регістрових переходів, розвиток гнучкості звуковедення; для чоловічих – подолання напруги у верхньому регістрі, формування м’якої атаки звуку та стабілізація позиції в перехідній зоні. Практика педагогів кафедри ХДАК підтверджує ефективність індивідуального підходу з урахуванням не лише морфологічних, а й емоційно-поведінкових параметрів кожного студента / студентки.Фахівцями проаналізовано відмінності у психоакустичному сприйнятті власного голосу студентами різної статі, що суттєво впливає на динаміку розвитку інтонаційної точності, тембрової стабільності та сценічної впевненості. У педагогічному процесі викладачами активно використовуються методичні прийоми, апробовані в Харківській державній академії культури, зокрема варіативне застосування вокалізів, робота над змішаними регістрами, поетапне ускладнення репертуару залежно від темпів психофізіологічної адаптації студента.У статті бґрунтовано важливість добору навчального матеріалу не лише за параметрами голосового типу (тенор, сопрано тощо), а й відповідно до емоційної чутливості, рівня сценічної готовності та індивідуального потенціалу самовираження.У підсумку наголошено на центральній ролі гнучкої, ґендерно-орієнтованої педагогічної моделі, яка реалізується викладачами кафедри хорового диригування та академічного співу ХДАК, і базується на глибокому розумінні взаємозв’язку фізіологічних, психофізіологічних та психологічних чинників вокального розвитку. Визначено перспективи подальших досліджень у напрямі ґендерно-орієнтованої вокальної педагогіки, зокрема в контексті професійної підготовки академічних співаків у мистецьких освітніх закладах.

Unggi Lee, Minji Jeon, Yunseo Lee et al.

Despite the development of various AI systems to support learning in various domains, AI assistance for art appreciation education has not been extensively explored. Art appreciation, often perceived as an unfamiliar and challenging endeavor for most students, can be more accessible with a generative AI enabled conversation partner that provides tailored questions and encourages the audience to deeply appreciate artwork. This study explores the application of multimodal large language models (MLLMs) in art appreciation education, with a focus on developing LLaVA-Docent, a model designed to serve as a personal tutor for art appreciation. Our approach involved design and development research, focusing on iterative enhancement to design and develop the application to produce a functional MLLM-enabled chatbot along with a data design framework for art appreciation education. To that end, we established a virtual dialogue dataset that was generated by GPT-4, which was instrumental in training our MLLM, LLaVA-Docent. The performance of LLaVA-Docent was evaluated by benchmarking it against alternative settings and revealed its distinct strengths and weaknesses. Our findings highlight the efficacy of the MMLM-based personalized art appreciation chatbot and demonstrate its applicability for a novel approach in which art appreciation is taught and experienced.

Bereket A. Yilma, Luis A. Leiva

Visual art (VA) recommendation is complex, as it has to consider the interests of users (e.g. museum visitors) and other stakeholders (e.g. museum curators). We study how to effectively account for key stakeholders in VA recommendations while also considering user-centred measures such as novelty, serendipity, and diversity. We propose MOSAIC, a novel multimodal multistakeholder-aware approach using state-of-the-art CLIP and BLIP backbone architectures and two joint optimisation objectives: popularity and representative selection of paintings across different categories. We conducted an offline evaluation using preferences elicited from 213 users followed by a user study with 100 crowdworkers. We found a strong effect of popularity, which was positively perceived by users, and a minimal effect of representativeness. MOSAIC's impact extends beyond visitors, benefiting various art stakeholders. Its user-centric approach has broader applicability, offering advancements for content recommendation across domains that require considering multiple stakeholders.

Linglin Liang, Nazik Hangeldiyeva

Ziv Epstein, Aaron Hertzmann, Laura Herman et al.

A new class of tools, colloquially called generative AI, can produce high-quality artistic media for visual arts, concept art, music, fiction, literature, video, and animation. The generative capabilities of these tools are likely to fundamentally alter the creative processes by which creators formulate ideas and put them into production. As creativity is reimagined, so too may be many sectors of society. Understanding the impact of generative AI - and making policy decisions around it - requires new interdisciplinary scientific inquiry into culture, economics, law, algorithms, and the interaction of technology and creativity. We argue that generative AI is not the harbinger of art's demise, but rather is a new medium with its own distinct affordances. In this vein, we consider the impacts of this new medium on creators across four themes: aesthetics and culture, legal questions of ownership and credit, the future of creative work, and impacts on the contemporary media ecosystem. Across these themes, we highlight key research questions and directions to inform policy and beneficial uses of the technology.

Ali Raza, Mohammad Rustom Al Nasar, Essam Said Hanandeh et al.

Kinematic motion detection aims to determine a person’s actions based on activity data. Human kinematic motion detection has many valuable applications in health care, such as health monitoring, preventing obesity, virtual reality, daily life monitoring, assisting workers during industry manufacturing, caring for the elderly. Computer vision-based activity recognition is challenging due to problems such as partial occlusion, background clutter, appearance, lighting, viewpoint, and changes in scale. Our research aims to detect human kinematic motions such as walking or running using smartphones’ sensor data within a high-performance framework. An existing dataset based on smartphones’ gyroscope and accelerometer sensor values is utilized for the experiments in our study. Sensor exploratory data analysis was conducted in order to identify valuable patterns and insights from sensor values. The six hyperparameters, tunned artificial indigence-based machine learning, and deep learning techniques were applied for comparison. Extensive experimentation showed that the ensemble learning-based novel ERD (ensemble random forest decision tree) method outperformed other state-of-the-art studies with high-performance accuracy scores. The proposed ERD method combines the random forest and decision tree models, which achieved a 99% classification accuracy score. The proposed method was successfully validated with the k-fold cross-validation approach.

Taikang Yuan, Junxing Zhu, Wuxin Wang et al.

Sea surface temperature (SST) prediction has attracted increasing attention, due to its crucial role in understanding the Earth’s climate and ocean system. Existing SST prediction methods are typically based on either physics-based numerical methods or data-driven methods. Physics-based numerical methods rely on marine physics equations and have stable and explicable outputs, while data-driven methods are flexible in adapting to data and are capable of detecting unexpected patterns. We believe that these two types of method are complementary to each other, and their combination can potentially achieve better performances. In this paper, a space-time partial differential equation (PDE) is employed to form a novel physics-based deep learning framework, named the space-time PDE-guided neural network (STPDE-Net), to predict daily SST. Comprehensive experiments for SST prediction were conducted, and the results proved that our method could outperform the traditional finite-difference forecast method and several state-of-the-art deep learning and physics-guided deep learning methods.

Fatima Conceição Silva, Paula Mello De Luca, Josué da Costa Lima-Junior

In the 18th century, English physician Edward Jenner laid the foundation for modern vaccination by achieving protection against variola [...]

Kemi Chen, Jing Chen, Huanqiang Zeng et al.

For compressed images and videos, quality enhancement is essential. Though there have been remarkable achievements related to deep learning, deep learning models are too large to apply to real-time tasks. Therefore, a fast multi-frame quality enhancement method for compressed video, named Fast-MFQE, is proposed to meet the requirement of video-quality enhancement for real-time applications. There are three main modules in this method. One is the image pre-processing building module (IPPB), which is used to reduce redundant information of input images. The second one is the spatio-temporal fusion attention (STFA) module. It is introduced to effectively merge temporal and spatial information of input video frames. The third one is the feature reconstruction network (FRN), which is developed to effectively reconstruct and enhance the spatio-temporal information. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods in terms of lightweight parameters, inference speed, and quality enhancement performance. Even at a resolution of 1080p, the Fast-MFQE achieves a remarkable inference speed of over 25 frames per second, while providing a PSNR increase of 19.6% on average when QP = 37.

Teresa Simón Cabodevilla , Susana Martín Leralta

Resumen: La intención del presente artículo es realizar una revisión de las investigaciones previas que se centran en el análisis de la expresión verbal de las emociones en lenguas adicionales. Dado el auge que el estudio en el campo de las emociones está teniendo en la Lingüística Aplicada desde inicios de los años 90 del siglo pasado, se precisa comenzar con un análisis esclarecedor de la terminología en relación a aquellos elementos lingüísticos de diversa índole que entran en juego a la hora de comunicar nuestras emociones o las de terceros, que pueden ser de tipo descriptivo o expresivo, según hagan referencia o expresen emociones. A partir de esta aclaración, se examinan los trabajos enfocados en el análisis del lenguaje descriptivo en la expresión oral de las emociones en una lengua adicional, concretamente los que abordan el léxico emocional, sus dimensiones (valencia y activación, entre otras) y otros aspectos identificados. El esbozo de tal estado de la cuestión pretende favorecer la interpretación de los hallazgos en el área, identificar las líneas actualmente abiertas y señalar ciertas repercusiones para la enseñanza de lenguas adicionales. Abstract: The aim of the present paper is to conduct a review of the previous research focused on the analysis of the verbal expression of emotions in additional languages. Due to the rise that the study in the field of emotions is having in Applied Linguistics since the early 90s of the past century, it is necessary to start with a clarifying analysis of the terminology used in relation to those linguistic elements of different nature that come into play when we communicate our emotions. These elements can be descriptive or expressive depending on if they refer or express emotions. From this clarification we examine different works focused on the analysis of the descriptive language in the oral expression of emotions in an additional language, specifically the ones that address the emotional vocabulary, their dimensions (valence and arousal, among others) and other identified aspects. This outline of the state of art intend to favour the interpretation of the findings in the field of study, identify the future lines of research and highlight some of the effects for the teaching of additional languages.

Flávio Coutinho, Luiz Chaimowicz

Iterating on creating pixel art character sprite sheets is essential to the game development process. However, it can take a lot of effort until the final versions containing different poses and animation clips are achieved. This paper investigates using conditional generative adversarial networks to aid the designers in creating such sprite sheets. We propose an architecture based on Pix2Pix to generate images of characters facing a target side (e.g., right) given sprites of them in a source pose (e.g., front). Experiments with small pixel art datasets yielded promising results, resulting in models with varying degrees of generalization, sometimes capable of generating images very close to the ground truth. We analyze the results through visual inspection and quantitatively with FID.

Ulisses Telemaco, Paulo Alencar, Donald Cowan et al.

Agility Assessment (AA) comprises tools, assessment techniques, and frameworks that focus on indicating how a company or a team is applying agile techniques and eventually pointing out problems in adopting agile practices at a project-level, organization-level or individual-level. There are many approaches for AA such as agility assessment models, agility checklists, agility surveys, and agility assessment tools. This report presents the state of the art approaches that support agility assessment.

Sudarsan Sadasivuni, Sumukh Prashant Bhanushali, Imon Banerjee et al.

Abstract This work presents an on-chip analog-to-information conversion technique that utilizes analog hyper-dimensional computing based on reservoir-computing paradigm to process electrocardiograph (ECG) signals locally in-sensor and reduce radio frequency transmission by more than three orders-of-magnitude. Instead of transmitting the naturally sparse ECG signal or extracted features, the on-chip analog-to-information converter analyzes the ECG signal through a nonlinear reservoir kernel followed by an artificial neural network, and transmits the prediction results. The proposed technique is demonstrated for detection of sepsis onset and achieves state-of-the-art accuracy and energy efficiency while reducing sensor power by $$159\times $$ 159 × with test-chips prototyped in 65 nm CMOS.

Marx Viana, Paulo Alencar, Everton Guimaraes et al.

The demand for creating increasingly dynamic, autonomous and proactive software systems is challenging for the traditional Multi-agent Systems (MASs) approaches. Such requirement has given rise to adaptive software agents approaches. At the same time, norm is an essential and challenging feature that still tends to be addressed in adaptive MAS. In fact, norms to regulate agent behavior is still a vague concept that has not been properly investigated in terms of modeling and implementation. Even though many researchers have proposed modeling languages to deal with different abstractions, these languages fail to support the modeling of abstractions, such as adaptation and norms. Even more severe is the fact that little has been done to support the systematic design of Adaptive Normative Multi-Agent Systems (ANMASs). To facilitate the design and development of ANMASs, this paper presents a new metamodel, as well as language support, as means to provide tools to enable software developers. The proposed metamodel fosters a better understanding of the way agents are able to change their behaviors to deal with norms and captures interactions between agent’s norms and adaptation. To this end, our research is organized into five steps: (i) a literature review to identify the limitations of existing approaches related to ANMAS modeling; (ii) propose a new metamodel to support adaptative and normative concepts; (iii) propose a new language for modeling ANMASs; (iv) perform a qualitative and quantitative evaluation of the proposed language using a real case scenario, and (v) an empirical evaluation. The proposed metamodel and its associated modeling language advances the state of the art in modeling MASs and the approach is assessed in terms of correctness, time and difficulty. Our initial results revealed that our approach can be feasibly applied in a real world application, and is less difficult to apply and requires less time in comparison with a traditional approach. As software applications become more dynamic and adaptive, we believe it is essential to support developers to model MASs with abstractions such as adaptive agents, norms and their relationships. Such information can be foundational to steer future research on modeling adaptive agents capable of understanding and dealing with norms and adaptation.