Hasil untuk "Aesthetics"

Yuxuan Yao, Yuxuan Chen, Hui Li et al.

Multimodal Diffusion Transformers (MMDiTs) for text-to-image generation maintain separate text and image branches, with bidirectional information flow between text tokens and visual latents throughout denoising. In this setting, we observe a prompt forgetting phenomenon: the semantics of the prompt representation in the text branch is progressively forgotten as depth increases. We further verify this effect on three representative MMDiTs--SD3, SD3.5, and FLUX.1 by probing linguistic attributes of the representations over the layers in the text branch. Motivated by these findings, we introduce a training-free approach, prompt reinjection, which reinjects prompt representations from early layers into later layers to alleviate this forgetting. Experiments on GenEval, DPG, and T2I-CompBench++ show consistent gains in instruction-following capability, along with improvements on metrics capturing preference, aesthetics, and overall text--image generation quality.

Raphael Lotan, Natali Marmor, Sharon Weiss et al.

<i>Background and Objectives</i>: The association between female breast size and spinal back pain is widely suggested in clinical practice but remains insufficiently quantified in general, non-surgical populations in the scientific literature. Larger breasts may increase biomechanical strain on the spine, contributing to musculoskeletal pain and reduced quality of life. This study aimed to evaluate the association between breast size and back pain in a general orthopedic population of young women. <i>Materials and Methods</i>: A cross-sectional study was conducted among 200 women aged 18–36 who attended orthopedic clinics for non-spinal complaints. Data were collected via structured telephone questionnaires, including demographics, self-reported breast size (cup and band), pain characteristics, and SF-12 quality of life scores. Binary logistic regression, ANOVA, and chi-square analyses assessed associations between breast size, pain presence, severity, and functional outcomes. <i>Results</i>: Back pain prevalence increased with breast size: only 4.9% of B cup participants reported backache, compared to 85% of DD/E cup participants. VAS scores rose from 0.3 ± 1.6 (B cup) to 6.0 ± 2.9 (DD/E cup). Each 1 cm increase in band length raised the odds of back pain by 19.8% (OR = 1.198, <i>p</i> < 0.001), while large cup size was associated with up to 12-fold increased odds of pain. Larger breast size was also significantly associated with work limitations and social impairment. <i>Conclusions</i>: Breast size was strongly associated with the presence and severity of back pain, particularly in the thoracic and cervical regions. Clinicians should consider breast size in the assessment of backache, and reduction mammaplasty may have therapeutic value beyond aesthetics.

Mengting Lu

Introduction: Autotransplantation combined with orthodontic mechanics improves graft survival by optimizing donor positioning. This case illustrates a stepwise approach integrating pre-surgical orthodontic preloading, intraoperative non-rigid fixation, and post-transplant alignment. Case description: A 28-year-old patient presented with a non-restorable mandibular first molar (46) due to caries/apical pathology. Orthodontic examination revealed Class I left/Class II right molar relationships, 5mm lower anterior crowding (increased Bolton ratio), elongation of maxillary first premolar (15), and erupted third molar (38) suitable for transplantation. Pre-surgical orthodontics (extraction of 41) resolved crowding and normalized Bolton ratio. Conventional archwires aligned teeth; distalization of 47 via push coil spring created space for 38. A 100g force via NiTi wire preloaded the donor tooth, adjusting root angulation. A 3D-printed replica reduced donor tooth extra-oral time, preserving periodontal viability. Atraumatic extraction of 46 was followed by retrograde filling. The donor tooth was positioned into the socket and secured with brackets/wire, allowing micro-mobility. Three months post-transplant, tooth 38 was integrated into the orthodontic system, achieving ideal Bolton ratio at 1-year follow-up. Discussion: Traditional rigid fixation risks periodontal trauma. Our preloading minimized surgical adjustments and preserved ligament viability. Non-rigid fixation with brackets allowed micro-mobility, aiding physiological adaptation. The 3D replica reduced handling time, enhancing graft survival. Conclusion/clinical significance: This approach preserved bone, avoided implant placement, and achieved functional aesthetics. Combining pre-surgical force application and non-rigid fixation improved survival and reduced treatment time, offering a viable alternative to conventional methods.

Shanlin Zhou, Xinpeng Wang, Jianxun Lian et al.

Trained on diverse human-authored texts, Large Language Models (LLMs) unlocked the potential for Creative Natural Language Generation (CNLG), benefiting various applications like advertising and storytelling. Nevertheless, CNLG still remains difficult due to two main challenges. (1) Multi-objective flexibility: user requirements are often personalized, fine-grained, and pluralistic, which LLMs struggle to satisfy simultaneously; (2) Interpretive complexity: beyond generation, creativity also involves understanding and interpreting implicit meaning to enhance users' perception. These challenges significantly limit current methods, especially in short-form text generation, in generating creative and insightful content. To address this, we focus on Chinese baby naming, a representative short-form CNLG task requiring adherence to explicit user constraints (e.g., length, semantics, anthroponymy) while offering meaningful aesthetic explanations. We propose NAMeGEn, a novel multi-agent optimization framework that iteratively alternates between objective extraction, name generation, and evaluation to meet diverse requirements and generate accurate explanations. To support this task, we further construct a classical Chinese poetry corpus with 17k+ poems to enhance aesthetics, and introduce CBNames, a new benchmark with tailored metrics. Extensive experiments demonstrate that NAMeGEn effectively generates creative names that meet diverse, personalized requirements while providing meaningful explanations, outperforming six baseline methods spanning various LLM backbones without any training.

Alexander Vinogradov

Generative image models have recently shown significant progress in image realism, leading to public concerns about their potential misuse for document forgery. This paper explores whether contemporary open-source and publicly accessible diffusion-based generative models can produce identity document forgeries that could realistically bypass human or automated verification systems. We evaluate text-to-image and image-to-image generation pipelines using multiple publicly available generative model families, including Stable Diffusion, Qwen, Flux, Nano-Banana, and others. The findings indicate that while current generative models can simulate surface-level document aesthetics, they fail to reproduce structural and forensic authenticity. Consequently, the risk of generative identity document deepfakes achieving forensic-level authenticity may be overestimated, underscoring the value of collaboration between machine learning practitioners and document-forensics experts in realistic risk assessment.

Guotao Shen, Ziheng Yan, Xin Jin et al.

In the research of video quality assessment (VQA), two-branch network has emerged as a promising solution. It decouples VQA with separate technical and aesthetic branches to measure the perception of low-level distortions and high-level semantics respectively. However, we argue that while technical and aesthetic perspectives are complementary, the technical perspective itself should be measured in semantic-aware manner. We hypothesize that existing technical branch struggles to perceive the semantics of high-resolution videos, as it is trained on local mini-patches sampled from videos. This issue can be hidden by apparently good results on low-resolution videos, but indeed becomes critical for high-resolution VQA. This work introduces SiamVQA, a simple but effective Siamese network for highre-solution VQA. SiamVQA shares weights between technical and aesthetic branches, enhancing the semantic perception ability of technical branch to facilitate technical-quality representation learning. Furthermore, it integrates a dual cross-attention layer for fusing technical and aesthetic features. SiamVQA achieves state-of-the-art accuracy on high-resolution benchmarks, and competitive results on lower-resolution benchmarks. Codes will be available at: https://github.com/srcn-ivl/SiamVQA

Juanxi Tian, Siyuan Li, Conghui He et al.

Current multimodal models aim to transcend the limitations of single-modality representations by unifying understanding and generation, often using text-to-image (T2I) tasks to calibrate semantic consistency. However, their reliance on static, single-image generation in training and evaluation leads to overfitting to static pattern matching and semantic fusion, while fundamentally hindering their ability to model dynamic processes that unfold over time. To address these constraints, we propose Envision-a causal event progression benchmark for chained text-to-multi-image generation. Grounded in world knowledge and structured by spatiotemporal causality, it reorganizes existing evaluation dimensions and includes 1,000 four-stage prompts spanning six scientific and humanities domains. To transition evaluation from single images to sequential frames and assess whether models truly internalize world knowledge while adhering to causal-temporal constraints, we introduce Envision-Score, a holistic metric integrating multi-dimensional consistency, physicality, and aesthetics. Comprehensive evaluation of 15 models (10 specialized T2I models, 5 unified models) uncovers: specialized T2I models demonstrate proficiency in aesthetic rendering yet lack intrinsic world knowledge. Unified multimodal models bridge this gap, consistently outperforming specialized counterparts in causal narrative coherence. However, even these unified architectures remain subordinate to closed-source models and struggle to overcome the core challenge of spatiotemporal consistency. This demonstrates that a focus on causally-isolated single images impedes multi-frame reasoning and generation, promoting static pattern matching over dynamic world modeling-ultimately limiting world knowledge internalization, generation.

Pierre-Marie Chauvin, Angèle Merlin, Xavier Fresquet et al.

This paper explores the integration of generative AI into the fashion design process. Drawing on insights from the January 2025 seminar ``Tisser le futur,'' it investigates how AI reshapes creative workflows, from ideation to prototyping, while interrogating the ethical, aesthetic, and labor implications. The paper highlights co-creative dynamics between humans and machines, the potential for aesthetic innovation, and the environmental and cultural challenges of algorithmic design.

Dr. Asmaa Ali Abd Alhamed khlifa

Advantages of the Egyptian contemporary art include experimentation and innovation. Like life, art is subject to the inevitability of development. Art has become individual and autonomous because it is a combination of creativity and ideology, and translation of what is inside the artist himself. Herbert Read finds that "The origin of modernism in art is the innovation of style and search for new approaches of expression that reflect the freedom and have dimensions that extend as roots that take and benefit from all previous approaches". When we refer to the heritage should be seen innovatively, and we can not take without deepening the understanding of the cultural content and philosophy and its own belief, and the Egyptian heritage is formed in its general fabric of multiple cultures have overlapped and combined and merged to make the total unity of that heritage, in our heritage meet the tributaries of the ancient Pharaonic, Coptic and Islamic uniquely makes them a strong current of aesthetics and distinct domes. With its philosophy, Islamic Art was a source of inspiration of modern arts. Islamic art was able to have a positive effect. This research tries to establish a relation between the external form and the ideology adopted by the artist in the Islamic ages… through abstraction, modification and use of (plant, geometric and scripture) ornaments, perforation, overlay, plating, etching, miniature and filling, and how it has become inspiring in the contemporary relief works in terms of abstraction, summarization, simplification, slabbing, avoidance of details, structure of form, balance of masses and relations of surfaces with each other, and repetition which is named later visual and dynamic art (optical illusion art). For this purpose, this research is conducted to determine some artistic features and formal relations that were inspired by artist from the Islamic heritage, such as repetition of its formations and how to use them by analysis of some examples of contemporary relief works and their affection by Islamic art. Research problem: The research can be formulated in the following questions 1-To what extent does repetition as a distinctive feature of Islamic art affect the affirmation of expressive values in contemporary works of bas-relief? 2-Possible utilization of the items of Islamic art and inspiration of its forms in contemporary formations of repetition- based relief sculpture?

Homa Pourriyahi, Homayoun Pourriahi, Hossein Najd Sepas

Introduction: Aneurysmorrhaphy, described as reduction aneurysmoplasty, partial aneurysmectomy, or vessel wall recalibration, can be considered a suitable surgical plan for true aneurysms of arteriovenous fistulas (AVFs), allowing for a dynamic approach to reconstruction of aneurysmal AVFs of different severities, ensuring salvage of the native access. Report: Six challenging cases of AVF aneurysms are presented, some with extremely dilated and tortuous megafistulas, for which three surgical technique variations were performed. The patients had a mean age of 59.2 years, 50% were female, with brachiocephalic (n = 5, 83.3%) or brachiobasilic (n = 1, 16.7%) AVFs. The fistulas were created an average of 4.67 years previously, and the aneurysms had an average maximum diameter of 37.5 mm (range 25–60 mm). Surgical indications were rupture risk, thrombosis, or outflow stenosis compromising haemodialysis, infections, and concerns for quality of life (affected by post-puncture bleedings, disfiguring aesthetics, pain, and discomfort). The surgical techniques were simple aneurysmorrhaphy (n = 3, 50%), aneurysmorrhaphy with partial excision of aneurysmal segment with end to end anastomosis of venous ends (n = 2, 33.3%), and aneurysmorrhaphy with establishment of new venous outflow (n = 1, 16.7%). All AVFs were patent post-operatively and at follow up (mean 5.6 months, median one month). Haemodialysis was resumed through the AVFs at a mean of 2.17 weeks post-operatively, with placement of an alternative route for haemodialysis in the meantime. No patients experienced post-operative complications. Discussion: Experience with the more challenging cases shows that aneurysmorrhaphy can still be considered an acceptable, flexible, and pertinent method for salvage of megafistulas, giving the surgeon the much needed versatility to adapt to anatomical and pathological variations, with high patency rates and minimal complications, especially when other treatment options are not possible in complicated cases. AVF salvage through aneurysmorrhaphy allows for a dynamic approach to the reconstruction of severely tortuous, dilated veins, ensuring patency of the native AVF.

Nicolás Perrone

El presente artículo tiene por objeto el análisis de la noción de agenciamiento de Gilles Deleuze en el marco de la teatralidad. Para ello, se examina la distinción entre dispositivo y agenciamiento. La comprensión y modulación de estas nociones, permite postular los conceptos de dispositivo de visibilidad y agenciamiento teatral, los cuales adquieren una función metodológica en el contexto de un pensamiento sobre el teatro y su forma de composición. De acuerdo con esto, el análisis plantea que los diversos modos de producción de teatralidad se entienden como poéticas que funcionan como máquinas abstractas, esto es, como un diagrama que permite una distribución de la composición escénica. Esto determina un dispositivo de visibilidad en el teatro, el cual se efectúa a través de agenciamientos teatrales que dan una forma singular a la distribución sensible de los elementos escénicos.

Martin Nöllenburg, Christian Pirker, Anna Rapberger et al.

The visualization of argumentation frameworks (AFs) is crucial for enabling a wide applicability of argumentative tools. However, their visualization is often considered only as an accompanying part of tools for computing semantics and standard graphical representations are used. We introduce a new visualization technique that draws an AF, together with an extension (as part of the input), as a 3-layer graph layout. Our technique supports the user to more easily explore the visualized AF, better understand extensions, and verify algorithms for computing semantics. To optimize the visual clarity and aesthetics of this layout, we propose to minimize edge crossings in our 3-layer drawing. We do so by an exact ILP-based approach, but also propose a fast heuristic pipeline. Via a quantitative evaluation, we show that the heuristic is feasible even for large instances, while producing at most twice as many crossings as an optimal drawing in most cases.

Tingyu Lin, Robert Sablatnig

In analyzing vast amounts of digitally stored historical image data, existing content-based retrieval methods often overlook significant non-semantic information, limiting their effectiveness for flexible exploration across varied themes. To broaden the applicability of image retrieval methods for diverse purposes and uncover more general patterns, we innovatively introduce a crucial factor from computational aesthetics, namely image composition, into this topic. By explicitly integrating composition-related information extracted by CNN into the designed retrieval model, our method considers both the image's composition rules and semantic information. Qualitative and quantitative experiments demonstrate that the image retrieval network guided by composition information outperforms those relying solely on content information, facilitating the identification of images in databases closer to the target image in human perception. Please visit https://github.com/linty5/CCBIR to try our codes.

Katarzyna Kozłowska, Marta Kazarców, Piotr Czarnecki

Introduction. Hook nail deformity is a common complication following fingertip amputations. Loss of distal bone support and palmar pulp tissue, results in the volar curving of the nailbed, which may cause pain, and aesthetic and functional problems. A few procedures have been described to address nail deformity, including flaps, skin and bone grafts, and microsurgical transfer. Unfortunately, none of the techniques provides reliably good and persistent correction.Case report. An 8-year-old boy sustained amputation of the distal phalanx of the middle finger and underwent surgical closure of the wound. After 4 years, the patient was admitted to our Department due to a deformed hook nail, which was aesthetically distressing. The hook nail was curved volarly and obliquely. The radiographs showed the lack of a significant part of the distal phalanx. Treatment. Surgical reconstruction of deficient distal phalanx was performed. The iliac bone graft, inserted into the distal phalanx, was stabilized with two K wires. A Pedicled flap of full-thickness from the thenar was used to cover skin loss over the fingertip. Pedicle division was performed at around 4 weeks. “K” wires were removed after 4 months.Results. The procedure was well-tolerated by the patient, and no complications occurred. Bone graft provided solid support for the nail bed during healing. Adequate growth and aesthetics of the hook nail were achieved. At 2 years follow-up, slight rotation of the nail was observed, which could have resulted from partial graft resorption and growth of the patient. The patient was satisfied with the treatment. Conclusions. Although perfect restoration of the nail bed length and pulp contour remains unobtainable, our result showed stable correction of the hook nail deformity.

Okta Firmansyah, Indira Kartini

Similar to the language of the Qur’an, the terminology will imply pleasure before ideological submission. This study explores several hypotheses regarding the pleasure-related aspects of the Qur’anic text, particularly in the context of the oral Qur’an. It is because achieving an aesthetic experience through the mouth is one way. Some of these issues have been addressed by the concepts of work and text (teks), as well as Roland Barthes’ aesthetics of textual pleasure (The Pleasure of the Text). The use of Barthes concepts is made to carry on semiotics’ work in the study of how to read the Qur’an and incorporate the Barthesian text theory into the same study. In comparison to the findings of this qualitative research, the Qur’an as an authoritative holy book is a work that has absolute and complete truth and completeness, which does not allow any textual changes. Muslims who reject this idea are also rejecting their faith in Almighty Allah. Since the Qur’an is so full of meaning, which is limitless and can never be fully understood, it is also a text. In light of this, the Qur’an will give its readers ample room to create new texts (read: tafsir). This is consistent with the principle, s}ah}ih likulli zaman wa makn, that the Qur’an will always be relevant to the world and its events. The Qur’an, which is mostly read by Muslims, will also make its readers happy at the same time.

Courtney L. Gallen, Courtney L. Gallen, Jessica N. Schachtner et al.

IntroductionThe incorporation of game features into cognitive tasks can inform us about the influence of reward and motivation on attention. Continuous performance tasks (CPTs), designed to assess attention abilities, are examples of cognitive tasks that have been targeted for the addition of game features. However, previous results have been mixed regarding how game elements affect attention abilities and task performance.MethodsHere, we studied if there were factors that predict which individuals exhibit changes in attention from game features added to a CPT. Participants (N = 94, aged 21–71) played a traditional CPT and a game CPT with identical mechanics, but featured engaging game elements (aesthetics, storyline, competition, feedback, and reward).ResultsWe first found corroborating evidence that game features have mixed effects on attention performance: most attention metrics of interest exhibited no overall difference between the traditional and game CPT, while game elements reduced performance for a few metrics. Importantly, we also found that specific behavioral and demographic profiles predicted individual differences in performance on the game CPT compared to the traditional CPT. Those with more attention difficulties (ADHD symptoms), more reward responsiveness, and younger adults performed better on the game CPT while, conversely, those with fewer ADHD symptoms, less reward responsiveness, and older adults performed better on the traditional CPT.DiscussionThese findings provide insights into how game features can influence attention in different individuals and have important implications for the use of game elements in cognitive tasks and training interventions.

Sriyadi, Aulina Finka, Hanifah Nurul et al.

Yogyakarta City is one of the areas that implements vegetable alleys to meet people’s food needs. However, in its implementation there are obstacles to the lack of participation of farmer group members. The study aims to determine the perception of the members of the farmer group towards the implementation of the vegetable aisle, and the factors related to the perception of the members of the farmer group towards the implementation of the vegetable aisle. The research was conducted in the Districts of Umbulharjo, Danurejan and Kotagede. In each sub-district, 4 farmer groups were taken and each farmer group was taken by 5 farmers so that a total of 60 respondents. Data obtained through interviews with a questionnaire. Data analysis used descriptive analysis and spearman rank correlation analysis. The research results show that the perception of farmer group members towards the vegetable aisle from technical and economic aspects is quite good, while from health, aesthetics and environmental aspects it is good. It is recommended that members of farmer groups participate more actively in the implementation of vegetable aisles.

Olga Yu. Antsyferova, Andrey A. Astvatsaturov, Irina V. Morozova et al.

On December 8, 2022, an international academic conference dedicated to the year 1922 as an important milestone in the history of American and European Modernism was held at the Russian State University of Humanities (Moscow). The conference aimed at the cultural reconstruction of 1922 and was organized by the Department of Comparative-Historical Literary Studies, Russian State University for the Humanities, and A.M. Gorky Institute of World Literature of the Russian Academy of Sciences. American literary history occupied a prominent place in the program of the conference. The plenary session was devoted to T.S. Eliot, whose poem The Waste Land was published in 1922. Olga Polovinkina (Russian State University for the Humanities, A.M. Gorky Institute of World Literature of the Russian Academy of Sciences) spoke about the importance of the aesthetics of the music hall for the strcture The Waste Land. Igor Shaitanov (Russian State University of Humanities, The Russian Presidential Academy of National Economy and Public Administration) drew a parallel between The Waste Land and Evegny Zamyatin's Alatyr’. Vassily Tolmatchoff (Lomonosov Moscow State University) suggested a new interpretation of the “Love Song of J. Alfred Prufrock”. A.A. Astvatsaturov (St. Petersburg State University) considered T.S. Eliot’s modernist work in comparison with the creative attitudes and self-fashioning of Henry Miller. Alexandra Zinovieva (Lomonosov Moscow State University) spoke about Countess Marie Louise Elisabeth Larisсh von Moennich, the heroine of T.S. Eliot’s The Waste Land, and her participation in German and Austrian cinematographic projects of the late 1910s — early 1920s. Olga Panova (A.M. Gorky Institute of World Literature of the Russian Academy of Sciences, Lomonosov Moscow State University) reconstructed the year 1922 in the history of the Harlem Renaissance. Irina Morozova (Russian State University of Humanities) presented the year 1922 as an important period in the history of American pharaohmania. Olga Antsyferova (St. Petersburg State University) analysed the book 1922: Literature, Culture, Politics (ed. by Jean-Michel Rabaté; Cambridge University Press, 2015) showing how the methodology of historical simultaneity works on the material of culture studies.

Claudia Lira, Manuel Rivera Espinoza

Presentación del dossier coordinado por Claudia Lira Latuz y Manuel Rivera Espinoza

John Holgate

The recent rise in radiographic and photographic technology in the examination and interpretation of works of art—which has accompanied the digitization of artistic creativity in the contemporary world—has greatly enhanced the power of the naked eye to view and understand the masterpieces of the past. Through modern ‘digital telescopes’ a new breed of art scientists has emerged to both enhance and challenge traditional art scholarship. In this paper, I will first review some of the major projects in this new field of informational aesthetics and provide examples, from the impressive discoveries of Maurizio Seracini and Pascal Cotte, to the magnificent photographic examination of the Ghent Altarpiece by Van der Snickt and his team at the National Gallery of Art in Washington. Secondly, I will present the results of my own three-year exploration of Leonardo da Vinci’s extant paintings and drawings using photographic magnification, leading to the identification of recurrent autographic images and motifs only visible through the lens of a digital camera. Finally, I will discuss the implications of these studies in the philosophy of photography, the world of art and the future of digital humanism.