Hasil untuk "Visual arts"

L. Verdoliva

With the rapid progress in recent years, techniques that generate and manipulate multimedia content can now provide a very advanced level of realism. The boundary between real and synthetic media has become very thin. On the one hand, this opens the door to a series of exciting applications in different fields such as creative arts, advertising, film production, and video games. On the other hand, it poses enormous security threats. Software packages freely available on the web allow any individual, without special skills, to create very realistic fake images and videos. These can be used to manipulate public opinion during elections, commit fraud, discredit or blackmail people. Therefore, there is an urgent need for automated tools capable of detecting false multimedia content and avoiding the spread of dangerous false information. This review paper aims to present an analysis of the methods for visual media integrity verification, that is, the detection of manipulated images and videos. Special emphasis will be placed on the emerging phenomenon of deepfakes, fake media created through deep learning tools, and on modern data-driven forensic methods to fight them. The analysis will help highlight the limits of current forensic tools, the most relevant issues, the upcoming challenges, and suggest future directions for research.

A. Anguissola

Anna Anguissola teaches classical archaeology at the University of Pisa. Her principal research on Greco-Roman visual, material and literary culture has focused on urban development, the relationship between Greek and Roman art, the history and techniques of ancient sculpture, the Greek and Latin literary sources on the figural arts and the reception of classical art in later periods. She is the author of Supports in Roman Marble Sculpture: Workshop Practice and Modes of Viewing (Cambridge 2018), Difficillima imitatio. Immagine e lessico delle copie tra Grecia e Roma (Rome 2012) and Intimità a Pompei: Riservatezza, condivisione e prestigio negli ambienti ad alcova di Pompei (Berlin 2010). She coordinates the University of Pisa’s field research in Pompeii’s Regio II and in the northern and southwestern burial grounds of Hierapolis in Phrygia.

H. Stuckey, J. Nobel

E. Cetinic, James She

Technologies related to artificial intelligence (AI) have a strong impact on the changes of research and creative practices in visual arts. The growing number of research initiatives and creative applications that emerge in the intersection of AI and art motivates us to examine and discuss the creative and explorative potentials of AI technologies in the context of art. This article provides an integrated review of two facets of AI and art: (1) AI is used for art analysis and employed on digitized artwork collections, or (2) AI is used for creative purposes and generating novel artworks. In the context of AI-related research for art understanding, we present a comprehensive overview of artwork datasets and recent works that address a variety of tasks such as classification, object detection, similarity retrieval, multimodal representations, and computational aesthetics, among others. In relation to the role of AI in creating art, we address various practical and theoretical aspects of AI Art and consolidate related works that deal with those topics in detail. Finally, we provide a concise outlook on the future progression and potential impact of AI technologies on our understanding and creation of art.

Riccardo Corvi, D. Cozzolino, G. Zingarini et al.

Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks (GAN). Very recently, methods based on diffusion models (DM) have been gaining the spotlight. In addition to providing an impressive level of photorealism, they enable the creation of text-based visual content, opening up new and exciting opportunities in many different application fields, from arts to video games. On the other hand, this property is an additional asset in the hands of malicious users, who can generate and distribute fake media perfectly adapted to their attacks, posing new challenges to the media forensic community. With this work, we seek to understand how difficult it is to distinguish synthetic images generated by diffusion models from pristine ones and whether current state-of-the-art detectors are suitable for the task. To this end, first we expose the forensics traces left by diffusion models, then study how current detectors, developed for GAN-generated images, perform on these new synthetic images, especially in challenging social-network scenarios involving image compression and resizing. Datasets and code are available at https:github.com/grip-unina/DMimageDetection.

Jonghwan Mun, Minsu Cho, Bohyung Han

This paper addresses the problem of text-to-video temporal grounding, which aims to identify the time interval in a video semantically relevant to a text query. We tackle this problem using a novel regression-based model that learns to extract a collection of mid-level features for semantic phrases in a text query, which corresponds to important semantic entities described in the query (e.g., actors, objects, and actions), and reflect bi-modal interactions between the linguistic features of the query and the visual features of the video in multiple levels. The proposed method effectively predicts the target time interval by exploiting contextual information from local to global during bi-modal interactions. Through in-depth ablation studies, we find out that incorporating both local and global context in video and text interactions is crucial to the accurate grounding. Our experiment shows that the proposed method outperforms the state of the arts on Charades-STA and ActivityNet Captions datasets by large margins, 7.44\% and 4.61\% points at Recall@tIoU=0.5 metric, respectively.

Han Yang, Ruimao Zhang, Xiaobao Guo et al.

Image visual try-on aims at transferring a target clothes image onto a reference person, and has become a hot topic in recent years. Prior arts usually focus on preserving the character of a clothes image (e.g. texture, logo, embroidery) when warping it to arbitrary human pose. However, it remains a big challenge to generate photo-realistic try-on images when large occlusions and human poses are presented in the reference person. To address this issue, we propose a novel visual try-on network, namely Adaptive Content Generating and Preserving Network (ACGPN). In particular, ACGPN first predicts semantic layout of the reference image that will be changed after try-on (e.g.long sleeve shirt→arm, arm→jacket), and then determines whether its image content needs to be generated or preserved according to the predicted semantic layout, leading to photo-realistic try-on and rich clothes details. ACGPN generally involves three major modules. First, a semantic layout generation module utilizes semantic segmentation of the reference image to progressively predict the desired semantic layout after try-on. Second, a clothes warping module warps clothes image according to the generated semantic layout, where a second-order difference constraint is introduced to stabilize the warping process during training.Third, an inpainting module for content fusion integrates all information (e.g. reference image, semantic layout, warped clothes) to adaptively produce each semantic part of human body. In comparison to the state-of-the-art methods, ACGPN can generate photo-realistic images with much better perceptual quality and richer fine-details.

Casey Reas, Benjamin Fry

Miriam de Souza Rossini, Luíza Alvim, Morgana Gama de Lima et al.

Monica Tavares, Chi-Nan Pai, Juliana Henno

Este trabajo pretende mostrar cómo el co-design, a partir de la estrategia del digital craft, puede favorecer la creación de prótesis personalizadas, lo que puede contribuir al fortalecimiento de la autoestima del usuario y su integración en la sociedad, minimizando así los estigmas sociales.

Felipe L. Garcia

Rongfei Li, Francis Assadian

Image-based visual servoing (IBVS) methods have been well developed and used in many applications, especially in pose (position and orientation) alignment. However, most research papers focused on developing control solutions when 3D point features can be detected inside the field of view. This work proposes an innovative feedforward-feedback adaptive control algorithm structure with the Youla Parameterization method. A designed feature estimation loop ensures stable and fast motion control when point features are outside the field of view. As 3D point features move inside the field of view, the IBVS feedback loop preserves the precision of the pose at the end of the control period. Also, an adaptive controller is developed in the feedback loop to stabilize the system in the entire range of operations. The nonlinear camera and robot manipulator model is linearized and decoupled online by an adaptive algorithm. The adaptive controller is then computed based on the linearized model evaluated at current linearized point. The proposed solution is robust and easy to implement in different industrial robotic systems. Various scenarios are used in simulations to validate the effectiveness and robust performance of the proposed controller.

Mansour Kolahkaj, Homeyra Salehi farsani

Introduction: In the field of visual artworks, being Iranian has always been the concern of some artists. It is sometimes depicted with symbolic Iranian elements or elements attributed to Iran that have explicit or implicit implications. In addition to visual elements, color has also played a role as an independent element in representing the concept of being Iranian. However, the problem of this research is: «From an Iranian artist's point of view, what color is a sign of being Iranian, or is it mostly used for this purpose, or do the painters agree on it as an Iranian color?» This issue has been the focus of discussion in other disciplines; however, this research was conducted aiming at identifying the most frequent colors in paintings whose subject was Iran and presenting the answer to the questions «What are the colors used for the concept of Iran in the works of some Iranian painters from 1991 to 2020 (1370s-1390s S.H.)» and «How these colors are used?»Research Method: This research data was collected using library sources, databases, and articles from reliable scientific journals. The data analysis was done using visual content analysis by collecting the works of Iranian painters from 1991 to 2020 (1370s-1390s S.H.). Accordingly, with the help of color separation software, these works were analyzed, and the most frequently used colors related to Iran were determined and then interpreted.Findings: In the works they created in the name of Iran or for this concept, according to their technique and method of work, Iranian painters used color in addition to shape to represent the concept of Iran. Considering the three colors used the most in this field, first, the Yellow (Pale Goldenrod-Khaki) range; second, the dark and light Blue range; and third, the Lacquer Red (Crimson-Maroon) range were applied. Also, among the works of 10 examined painters, seven painters, along with color, have used visual elements related to Iran, mainly with a clear implication, which is often a representation of Iran's architectural works.Conclusion: Green, Red, and White are the three colors of the Iranian flag, and they have a symbolic expression to represent the concept of Iran. As the color of Iran, they have been used less by painters and designers. Therefore, in addition to the colors of the Iranian flag, there are other colors in the color palette of Iranian painters, which are referred to as the colors of Iran. Hence, in addition to symbolic elements, the painters implicitly used the color associated with Iran for their visual expression. Also, a type of color correlation has been seen in the works of painters whose visual and symbolic elements of architectural landscapes were the basis of their work.

Andy Retana Bustamante

La presente investigación se sumerge la exploración de la soledad masculina a través de dos aclamados largometrajes de animación stop motion: Anomalisa (2015) dirigida por Charlie Kaufman y Duke Johnson, así como Mary and Max (2003) dirigida por Adam Elliot. La misma se llevará a cabo a través de un análisis multimodal, que permitirá examinar cómo se utilizan distintos recursos semióticos para construir historias que reflejan la soledad masculina y problemas de salud mental, considerando las normas de género desde una perspectiva interseccional. Desde este enfoque interdisciplinario, se busca correlacionar técnicas de análisis semiótico-sociales con estudios de género, para detectar las particularidades con las que ambas animaciones presentan a sus personajes masculinos lidiando con la soledad y el aislamiento, así como sus respectivos problemas de salud mental.

فاطمه نورشهرکی, جواد امین خندقی, جمال عرب زاده

بازنمایی طبیعت یکی از موضوعات مهم در نقاشی به‌شمار می‌رود. در این میان، بازنمایی دریا، به‌دلیل ویژگی‌های منحصربه‌فردی که دارد، اهمیت و جذابیت دوچندان دارد. در بستر فلسفه نیز از منظرهای مختلفی به طبیعت پرداخته شده است. در این باره، مفهوم کلیدی «امر والا» در فلسفه کانت جایگاه ویژه‌ای دارد. این مفهوم می‌تواند ابعاد جدیدی از بازنمایی طبیعت را روشن سازد. بازنمایی امواج دریا به‌مثابه ابژه‌ای -که می‌تواند نشانی از امر والا باشد- در جنبش­های هنری قرن نوزدهم بروز داشته است. پژوهش حاضر در جست‌وجوی ارایه خوانشی از بازنمایی امواج دریا در نقاشی‌های رمانتیک قرن نوزدهم اروپا مبتنی بر امر والای کانت است. در این پژوهش، با روش توصیفی-تحلیلی و بهره­گیری از روش گردآوری کتابخانه­ای در جمع­آوری اطلاعات و نمونه‌گیری گزینشی، از میان آثار نقاشی دریا در سده نوزدهم اروپا، پنج اثر انتخاب شده و به‌شیوه تحلیل کیفی، مورد بررسی قرار گرفته‌اند.­ این پژوهش نشان می‌دهد که، الگوی بازنمایی دریا در نقاشی رمانتیک قرن نوزدهم، بنا بر نوع امر والا متفاوت است. امر والای پویا در آثار مورد بررسی، از طریق نمایش قدرت و قهر دریا تصویر شده است. والای ریاضی نیز با نمایش عظمت و وسعت و گستردگی دریا صورت پذیرفته است. با نگاهی دقیق­تر به آثار تحلیلی، درمی­یابیم که سبک رمانتسیم، برای نمایش قدرت طبیعت، بیان وقایع و رخدادها، توجه به معنویت و جنبه­های روحانی، واکنش بر انقلاب صنعتی و در برخی موارد، رویدادهای سیاسی به‌کار رفته است.

N. Jannsen, J. De Ridder, D. Seynaeve et al.

PLAnetary Transits and Oscillations of stars (PLATO) is the ESA M3 space mission dedicated to detect and characterise transiting exoplanets including information from the asteroseismic properties of their stellar hosts. The uninterrupted and high-precision photometry provided by space-borne instruments such as PLATO require long preparatory phases. An exhaustive list of tests are paramount to design a mission that meets the performance requirements, and as such, simulations are an indispensable tool in the mission preparation. To accommodate PLATO's need of versatile simulations prior to mission launch - that at the same time describe accurately the innovative but complex multi-telescope design - we here present the end-to-end PLATO simulator specifically developed for the purpose, namely PlatoSim. We show step-by-step the algorithms embedded into the software architecture of PlatoSim that allow the user to simulate photometric time series of CCD images and light curves in accordance to the expected observations of PLATO. In the context of the PLATO payload, a general formalism of modelling, end-to-end, incoming photons from the sky to the final measurement in digital units is discussed. We show the strong predictive power of PlatoSim through its diverse applicability and contribution to numerous working groups within the PLATO Mission Consortium. This involves the on-going mechanical integration and alignment, performance studies of the payload, the pipeline development and assessments of the scientific goals. PlatoSim is a state-of-the-art simulator that is able to produce the expected photometric observations of PLATO to a high level of accuracy. We demonstrate that PlatoSim is a key software tool for the PLATO mission in the preparatory phases until mission launch and prospectively beyond.

Diederik Aerts, Lester Beltran

As a result of the identification of 'identity' and 'indistinguishability' and strong experimental evidence for the presence of the associated Bose-Einstein statistics in human cognition and language, we argued in previous work for an extension of the research domain of quantum cognition. In addition to quantum complex vector spaces and quantum probability models, we showed that quantization itself, with words as quanta, is relevant and potentially important to human cognition. In the present work, we build on this result, and introduce a powerful radiation quantization scheme for human cognition. We show that the lack of independence of the Bose-Einstein statistics compared to the Maxwell-Boltzmann statistics can be explained by the presence of a 'meaning dynamics', which causes words to be attracted to the same words. And so words clump together in the same states, a phenomenon well known for photons in the early years of quantum mechanics, leading to fierce disagreements between Planck and Einstein. Using a simple example, we introduce all the elements to get a better and detailed view of this 'meaning dynamics', such as micro and macro states, and Maxwell-Boltzmann, Bose-Einstein and Fermi-Dirac numbers and weights, and compare this example and its graphs, with the radiation quantization scheme of a Winnie the Pooh story, also with its graphs. By connecting a concept directly to human experience, we show that entanglement is a necessity for preserving the 'meaning dynamics' we identified, and it becomes clear in what way Fermi-Dirac addresses human memory. Within the human mind, as a crucial aspect of memory, in spaces with internal parameters, identical words can nevertheless be assigned different states and hence realize locally and contextually the necessary distinctiveness, structured by a Pauli exclusion principle, for human thought to thrive.

Fanny Cardin

Willem van Jaarsveld, Joachim Arts

We consider the canonical periodic review lost sales inventory system with positive lead-times and stochastic i.i.d. demand under the average cost criterion. We introduce a new policy that places orders such that the expected inventory level at the time of arrival of an order is at a fixed level and call it the Projected Inventory Level (PIL) policy. We prove that this policy has a cost-rate superior to the equivalent system where excess demand is back-ordered instead of lost and is therefore asymptotically optimal as the cost of losing a sale approaches infinity under mild distributional assumptions. We further show that this policy dominates the constant order policy for any finite lead-time and is therefore asymptotically optimal as the lead-time approaches infinity for the case of exponentially distributed demand per period. Numerical results show this policy also performs superior relative to other policies.

Maziar Shafaee, Mohammad Hosein Sabour, Armin Abdehkakha et al.

A Visual investigation of spray cone angle for different air-blast atomizers and flow conditions is described. Liquid jets are exposed to high gas stream with specific relative angle. Using high speed camera, spray cone angle over a range of Reynolds number 4x104 to 9x104 and Weber number 1 to 140 is studied, followed by laser-based diagnosis of particle distribution and Sauter mean diameter. The results show that for high Reynolds and Weber number, the cone angle is independent of flow condition, and is only dependent on geometry of atomizer, including orifice diameter with significant effect on cone angle, Sauter mean diameter and particle distribution