Hasil untuk "Style. Composition. Rhetoric"

Mauro Tulli

Lo scopo di questo contributo è organizzare un pur veloce schema degli orientamenti che ha il dibattito sulle parole delle Muse che nella Teogonia, per la scena dell’investitura, Esiodo inserisce amalgamando ben precisi modelli di Omero, con arte allusiva, il discorso delle Sirene, il discorso di Eumeo nell’Odissea e, al centro, il commento al discorso di Etone di Creta. Per le cose vere, ἀληθέα, qui emerge un attrito polare con le molte cose false, ψεύδεα πολλά, che sembrano reali, ἐτύμοισιν ὁμοῖα. Per la critica, il rifiuto colpisce la menzogna con la negazione dell’identità o indica la teoria dell’εἰκὼς λόγος, della finzione, che Aristotele deriva da Gorgia e da Platone. Ma Tucidide, con la VII Nemea di Pindaro, è un sostegno per immaginare un terzo campo: il racconto che trova un codice nell’αὔξησις, nell’amplificazione, il racconto che non offre la base conciliabile con le cose vere.

Thierry Herman

L’article propose et défend un modèle de cartographie du raisonnement qui vise avant tout une description aussi exhaustive que possible des mouvements argumentatifs d’un texte en langue naturelle. Après avoir évoqué différentes impasses des approches existantes – la logique informelle, à l’origine de ces cartes, l’analyse computationnelle de l’argumentation et la linguistique du texte –, il est envisagé une approche fonctionnelle interdisciplinaire qui repense la manière de segmenter un texte et se confronte aussi à des données langagières pas toujours prises en compte dans l’approche philosophique de la carte de l’argumentation. Une typologie de fonctions argumentatives et un mode de représentation de ces fonctions est abordé et testé sur un exemple complexe. Une réflexion sur les enjeux des cartes, entre outil pédagogique et outil scientifique, traverse l’ensemble de l’article.

Haoyu Zheng, Qifan Yu, Binghe Yu et al.

Diffusion models have achieved remarkable progress in image and video stylization. However, most existing methods focus on single-style transfer, while video stylization involving multiple styles necessitates seamless transitions between them. We refer to this smooth style transition between video frames as video style morphing. Current approaches often generate stylized video frames with discontinuous structures and abrupt style changes when handling such transitions. To address these limitations, we introduce SOYO, a novel diffusion-based framework for video style morphing. Our method employs a pre-trained text-to-image diffusion model without fine-tuning, combining attention injection and AdaIN to preserve structural consistency and enable smooth style transitions across video frames. Moreover, we notice that applying linear equidistant interpolation directly induces imbalanced style morphing. To harmonize across video frames, we propose a novel adaptive sampling scheduler operating between two style images. Extensive experiments demonstrate that SOYO outperforms existing methods in open-domain video style morphing, better preserving the structural coherence of video frames while achieving stable and smooth style transitions.

Hongda Liu, Longguang Wang, Ye Zhang et al.

Global effective receptive field plays a crucial role for image style transfer (ST) to obtain high-quality stylized results. However, existing ST backbones (e.g., CNNs and Transformers) suffer huge computational complexity to achieve global receptive fields. Recently, the State Space Model (SSM), especially the improved variant Mamba, has shown great potential for long-range dependency modeling with linear complexity, which offers a approach to resolve the above dilemma. In this paper, we develop a Mamba-based style transfer framework, termed SaMam. Specifically, a mamba encoder is designed to efficiently extract content and style information. In addition, a style-aware mamba decoder is developed to flexibly adapt to various styles. Moreover, to address the problems of local pixel forgetting, channel redundancy and spatial discontinuity of existing SSMs, we introduce both local enhancement and zigzag scan. Qualitative and quantitative results demonstrate that our SaMam outperforms state-of-the-art methods in terms of both accuracy and efficiency.

Yanxia Feng, Noel Ringeisen, Eric R. Dufresne et al.

Porous gels -- gels with solvent-filled pores that are much larger than their mesh size -- are widely used in engineering and biomedical applications due to their tunable mechanics, high water content, and selective permeability. Among various strategies to create porous gels, polymerization-induced phase separation (PIPS) has shown particular promise. However, the conditions that trigger and control PIPS remain poorly understood. Here, we systematically investigate the influence of solvent quality, polymeric precursor molecular weight, and polymer concentration on phase separation in polymerizing poly(ethylene glycol) diacrylate gels. We find that phase separation occurs when the precursor solution concentration is below the overlap concentration. Phase-separated gels have a pore geometry that is controlled by solvent quality: better solvents result in smaller pores, while worse solvents can create superporous, highly-absorbant gels. Motivated by our results, we propose a theory that predicts when phase separation occurs in polymerizing gels, applicable across a wide range of polymer/solvent gel systems. Our results provide a framework for the rational design of porous gels.

Adil Meric, Umut Kocasari, Matthias Nießner et al.

Neural Radiance Fields (NeRF) have emerged as a powerful tool for creating highly detailed and photorealistic scenes. Existing methods for NeRF-based 3D style transfer need extensive per-scene optimization for single or multiple styles, limiting the applicability and efficiency of 3D style transfer. In this work, we overcome the limitations of existing methods by rendering stylized novel views from a NeRF without the need for per-scene or per-style optimization. To this end, we take advantage of a generalizable NeRF model to facilitate style transfer in 3D, thereby enabling the use of a single learned model across various scenes. By incorporating a hypernetwork into a generalizable NeRF, our approach enables on-the-fly generation of stylized novel views. Moreover, we introduce a novel flow-based multi-view consistency loss to preserve consistency across multiple views. We evaluate our method across various scenes and artistic styles and show its performance in generating high-quality and multi-view consistent stylized images without the need for a scene-specific implicit model. Our findings demonstrate that this approach not only achieves a good visual quality comparable to that of per-scene methods but also significantly enhances efficiency and applicability, marking a notable advancement in the field of 3D style transfer.

Sizhe Zheng, Pan Gao, Peng Zhou et al.

Style transfer aims to render an image with the artistic features of a style image, while maintaining the original structure. Various methods have been put forward for this task, but some challenges still exist. For instance, it is difficult for CNN-based methods to handle global information and long-range dependencies between input images, for which transformer-based methods have been proposed. Although transformers can better model the relationship between content and style images, they require high-cost hardware and time-consuming inference. To address these issues, we design a novel transformer model that includes only the encoder, thus significantly reducing the computational cost. In addition, we also find that existing style transfer methods may lead to images under-stylied or missing content. In order to achieve better stylization, we design a content feature extractor and a style feature extractor, based on which pure content and style images can be fed to the transformer. Finally, we propose a novel network termed Puff-Net, i.e., pure content and style feature fusion network. Through qualitative and quantitative experiments, we demonstrate the advantages of our model compared to state-of-the-art ones in the literature.

Jesús Miguel Delgado Del Aguila

Stefano Arduini es catedrático de Lingüística en la Universidad de Roma Link Campus, donde es Presidente del Departamento de Licenciatura en Artes, Música y Artes Escénicas y Prorector para la Tercera Misión. Ha enseñado Lingüística General y Teoría de la Traducción en la Universidad de Urbino; Lingüística en la Universidad de Estudios Internacionales de Roma y en la Universidad de Módena; y Literatura Comparada en la Universidad de Alicante y en la Universidad Autónoma de Madrid.

Sunder Ali Khowaja, Lewis Nkenyereye, Ghulam Mujtaba et al.

With the surge in emerging technologies such as Metaverse, spatial computing, and generative AI, the application of facial style transfer has gained a lot of interest from researchers as well as startups enthusiasts alike. StyleGAN methods have paved the way for transfer-learning strategies that could reduce the dependency on the huge volume of data that is available for the training process. However, StyleGAN methods have the tendency of overfitting that results in the introduction of artifacts in the facial images. Studies, such as DualStyleGAN, proposed the use of multipath networks but they require the networks to be trained for a specific style rather than generating a fusion of facial styles at once. In this paper, we propose a FusIon of STyles (FIST) network for facial images that leverages pre-trained multipath style transfer networks to eliminate the problem associated with lack of huge data volume in the training phase along with the fusion of multiple styles at the output. We leverage pre-trained styleGAN networks with an external style pass that use residual modulation block instead of a transform coding block. The method also preserves facial structure, identity, and details via the gated mapping unit introduced in this study. The aforementioned components enable us to train the network with very limited amount of data while generating high-quality stylized images. Our training process adapts curriculum learning strategy to perform efficient, flexible style and model fusion in the generative space. We perform extensive experiments to show the superiority of FISTNet in comparison to existing state-of-the-art methods.

Yueming Lyu, Yue Jiang, Bo Peng et al.

Artistic style transfer aims to transfer the style of an artwork to a photograph while maintaining its original overall content. Many prior works focus on designing various transfer modules to transfer the style statistics to the content image. Although effective, ignoring the clear disentanglement of the content features and the style features from the first beginning, they have difficulty in balancing between content preservation and style transferring. To tackle this problem, we propose a novel information disentanglement method, named InfoStyler, to capture the minimal sufficient information for both content and style representations from the pre-trained encoding network. InfoStyler formulates the disentanglement representation learning as an information compression problem by eliminating style statistics from the content image and removing the content structure from the style image. Besides, to further facilitate disentanglement learning, a cross-domain Information Bottleneck (IB) learning strategy is proposed by reconstructing the content and style domains. Extensive experiments demonstrate that our InfoStyler can synthesize high-quality stylized images while balancing content structure preservation and style pattern richness.

Dan Ruta, Gemma Canet Tarres, Alexander Black et al.

Representation learning aims to discover individual salient features of a domain in a compact and descriptive form that strongly identifies the unique characteristics of a given sample respective to its domain. Existing works in visual style representation literature have tried to disentangle style from content during training explicitly. A complete separation between these has yet to be fully achieved. Our paper aims to learn a representation of visual artistic style more strongly disentangled from the semantic content depicted in an image. We use Neural Style Transfer (NST) to measure and drive the learning signal and achieve state-of-the-art representation learning on explicitly disentangled metrics. We show that strongly addressing the disentanglement of style and content leads to large gains in style-specific metrics, encoding far less semantic information and achieving state-of-the-art accuracy in downstream multimodal applications.

Valeria Efimova, Artyom Chebykin, Ivan Jarsky et al.

Neural style transfer draws researchers' attention, but the interest focuses on bitmap images. Various models have been developed for bitmap image generation both online and offline with arbitrary and pre-trained styles. However, the style transfer between vector images has not almost been considered. Our research shows that applying standard content and style losses insignificantly changes the vector image drawing style because the structure of vector primitives differs a lot from pixels. To handle this problem, we introduce new loss functions. We also develop a new method based on differentiable rasterization that uses these loss functions and can change the color and shape parameters of the content image corresponding to the drawing of the style image. Qualitative experiments demonstrate the effectiveness of the proposed VectorNST method compared with the state-of-the-art neural style transfer approaches for bitmap images and the only existing approach for stylizing vector images, DiffVG. Although the proposed model does not achieve the quality and smoothness of style transfer between bitmap images, we consider our work an important early step in this area. VectorNST code and demo service are available at https://github.com/IzhanVarsky/VectorNST.

Zhichao Wang, Xinsheng Wang, Qicong Xie et al.

In addition to conveying the linguistic content from source speech to converted speech, maintaining the speaking style of source speech also plays an important role in the voice conversion (VC) task, which is essential in many scenarios with highly expressive source speech, such as dubbing and data augmentation. Previous work generally took explicit prosodic features or fixed-length style embedding extracted from source speech to model the speaking style of source speech, which is insufficient to achieve comprehensive style modeling and target speaker timbre preservation. Inspired by the style's multi-scale nature of human speech, a multi-scale style modeling method for the VC task, referred to as MSM-VC, is proposed in this paper. MSM-VC models the speaking style of source speech from different levels. To effectively convey the speaking style and meanwhile prevent timbre leakage from source speech to converted speech, each level's style is modeled by specific representation. Specifically, prosodic features, pre-trained ASR model's bottleneck features, and features extracted by a model trained with a self-supervised strategy are adopted to model the frame, local, and global-level styles, respectively. Besides, to balance the performance of source style modeling and target speaker timbre preservation, an explicit constraint module consisting of a pre-trained speech emotion recognition model and a speaker classifier is introduced to MSM-VC. This explicit constraint module also makes it possible to simulate the style transfer inference process during the training to improve the disentanglement ability and alleviate the mismatch between training and inference. Experiments performed on the highly expressive speech corpus demonstrate that MSM-VC is superior to the state-of-the-art VC methods for modeling source speech style while maintaining good speech quality and speaker similarity.

Covadonga Valdaliso Casanova, Carmen Benítez Guerrero, Ricardo Pichel et al.

En los últimos siglos de la Edad Media se multiplicó la actividad de los llamados ‘escribanos historiadores’, profesionales de la escritura que desempeñaron labores historiográficas. Este trabajo presenta un ejemplo de ello: una lista de anales que cuenta además con la particularidad de entrelazar la historia general con informaciones de tipo local y familiar, y aporta datos para inferir el nombre de su autor

Ilaria Cennamo

Marie Chandelier, Paola Paissa

The multi-factorial nature of the environmental crisis favors the use of enumeration in argumentative discourses. In order to study the rhetorical functions of long enumerations, we collected 131 view articles published in the daily newspaper Le Monde (2006-2018) and related to biodiversity. Our study showed that long enumerations were mainly used in three different perspectives: alerting to the gravity of the environmental crisis, promoting actions to stop environmental destruction, underlying the detrimental effects of the rhetorical functions of amplification. In our corpus, the use of the rhetoric of amplification is associated with an axiological vocabulary. Such axiological terms give an emotional lecture of the co-enumerated items and do not explicit the common properties of the multiple entities that characterize the environmental crisis.

Karl Munson, Anish Savla, Chih-Kai Ting et al.

Style is a significant component of natural language text, reflecting a change in the tone of text while keeping the underlying information the same. Even though programming languages have strict syntax rules, they also have style. Code can be written with the same functionality but using different language features. However, programming style is difficult to quantify, and thus as part of this work, we define style attributes, specifically for Python. To build a definition of style, we utilized hierarchical clustering to capture a style definition without needing to specify transformations. In addition to defining style, we explore the capability of a pre-trained code language model to capture information about code style. To do this, we fine-tuned pre-trained code-language models and evaluated their performance in code style transfer tasks.

Emmanuel Deruty, Maarten Grachten

Although the use of AI tools in music composition and production is steadily increasing, as witnessed by the newly founded AI song contest, analysis of music produced using these tools is still relatively uncommon as a mean to gain insight in the ways AI tools impact music production. In this paper we present a case study of "Melatonin", a song produced by extensive use of BassNet, an AI tool originally designed to generate bass lines. Through analysis of the artists' work flow and song project, we identify style characteristics of the song in relation to the affordances of the tool, highlighting manifestations of style in terms of both idiom and sound.

Fabio Camilletti

This essay examines the influence of Plutarch’s Life of Brutus on Mary Shelley’s Frankenstein, arguing that the relationship between Brutus and his «evil genius» provides Shelley with a model for characterizing the pair of Victor Frankenstein and his Creature. By considering the broader context of Plutarch’s reception from the sixteenth through the early nineteenth centuries, and particularly the construction of Brutus as a ghost-seer, a clinical obsessive, or a revolutionary icon, the essay examines the Brutus/Victor parallel as actual and/or symbolic parricides, shedding new light on Shelley’s failed representation of the French Revolution in her novel.

Nicholas Kolkin

It seems easy to imagine a photograph of the Eiffel Tower painted in the style of Vincent van Gogh's 'The Starry Night', but upon introspection it is difficult to precisely define what this would entail. What visual elements must an image contain to represent the 'content' of the Eiffel Tower? What visual elements of 'The Starry Night' are caused by van Gogh's 'style' rather than his decision to depict a village under the night sky? Precisely defining 'content' and 'style' is a central challenge of designing algorithms for artistic style transfer, algorithms which can recreate photographs using an artwork's style. My efforts defining these terms, and designing style transfer algorithms themselves, are the focus of this thesis. I will begin by proposing novel definitions of style and content based on optimal transport and self-similarity, and demonstrating how a style transfer algorithm based on these definitions generates outputs with improved visual quality. Then I will describe how the traditional texture-based definition of style can be expanded to include elements of geometry and proportion by jointly optimizing a keypoint-guided deformation field alongside the stylized output's pixels. Finally I will describe a framework inspired by both modern neural style transfer algorithms and traditional patch-based synthesis approaches which is fast, general, and offers state-of-the-art visual quality.