Letteratura scientifica selezionata sul tema "Transfert de style"
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Consulta la lista di attuali articoli, libri, tesi, atti di convegni e altre fonti scientifiche attinenti al tema "Transfert de style".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Articoli di riviste sul tema "Transfert de style":
1
Duez, Bernard. "Le transfert comme paradigme processuel de la groupalité psychique : de l'habitude au style". Revue de psychothérapie psychanalytique de groupe 45, n. 2 (2005): 31. http://dx.doi.org/10.3917/rppg.045.0031.
2
Okubo, Miki. "La notion "gothique" traduite dans la culture pop du Japon contemporain". Jangada: crítica | literatura | artes 1, n. 17 (6 agosto 2021): 390–408. http://dx.doi.org/10.35921/jangada.v1i17.351.
Abstract (sommario):
Le mouvement « Gothic and Lolita » est à la fois le style vestimentaire et une pratique philosophique développée dans la société japonaise depuis les années 1990, son influence se fait sentir dans différents milieux culturels et son origine est issue du roman gothique. Le présent article met en lumière un processus unique du transfert culturel de la notion « gothique » dans la culture japonaise contemporaine comme un phénomène culturel issu de différentes cultures, évolué au sein d’une culture autochtone plus traditionnelle. L’association de la notion « gothique » à la notion « lolita » est expliquée par deux causes : l’admiration totale des Japonais envers la culture occidentale et l’infantilisme comme trait culturel. Même si le concept de Lolita est emprunté au roman de Nabokov, sa signification est déformée dans le style Gothic and Lolita. Cette mode et sa pratique ont reçu une signification complexe de défense de soi avec des éléments gothiques afin de préserver à jamais la nature de Lolita et de refuser d’être consommée dans la société en tant que femme mûre. De cette façon, le concept gothique a été transformé et aliéné afin de s’adapter aux idées culturelles autochtones dans le transfert culturel vers la culture japonaise.
3
Koffi, Vivi, e Jean Lorrain. "L’intégration du successeur dans l’équipe de gestion des entreprises familiales : le cas des femmes chefs d’entreprise". Revue internationale P.M.E. 18, n. 3-4 (16 febbraio 2012): 73–92. http://dx.doi.org/10.7202/1008483ar.
Abstract (sommario):
La problématique de la relève dans les entreprises familiales préoccupe de plus en plus les chercheurs et les professionnels du milieu des affaires. Étant donné le nombre très important de transferts et la fréquence de leurs échecs, comment peut-on parler de relève sans s’intéresser à l’intégration du successeur dans l’équipe de gestion en vue d’assurer la pérennité de l’entreprise familiale ? De plus, compte tenu de l’importance grandissante de l’apport des femmes chefs d’entreprises dans l’économie des pays, l’objectif de cet article est de faire un survol des différents travaux qui portent, d’une part, sur le transfert managérial dans une optique d’intégration et, d’autre part, sur la particularité du style féminin des femmes chefs d’entreprises lors de l’intégration de leurs successeurs.
4
Gold, Iwala. "L’emprunt En Traduction". Tasambo Journal of Language, Literature, and Culture 3, n. 01 (15 febbraio 2024): 390–95. http://dx.doi.org/10.36349/tjllc.2024.v03i01.045.
Abstract (sommario):
Dans un monde où les connaissances évoluent d'une manière de plus en plus alerte, le transfert des mots d’une langue à une autre, en forme de l’emprunt, devient essentiel pour enrichir le vocabulaire des langues de travail. L’emprunt c’est l’acte de maintenir certains mots du texte de départ dans le texte d’arrivée, soit par manque d’équivalence soit style et goût du traducteur. Puisque le but de la traduction est le transfert d’une réalité idéologique, médical, religieux ou politique, d’une langue à une autre pour le bien de l’humanité, le transfert des lexiques devint aussi une évidence. Notre object est ici de montrer que l’emprunt est l’un des procédés de la traduction plutôt qu’un handicap lexical ou de vocabulaire. Cet article se base sur la théorie de la pertinence qui insiste sur le principe dans l’économie du langage selon lequel le traducteur ne traduit que ce qui est pertinent. Donc nous préconisons la procédure de ne traduire et de n’employer que ce qui est pertinent dans la pratique de la traduction.
5
Lonvaud-Funel, Aline. "La désacidification biologique des vins. Etat de la question, perspectives d'avenir". OENO One 28, n. 2 (30 giugno 1994): 161. http://dx.doi.org/10.20870/oeno-one.1994.28.2.1149.
Abstract (sommario):
<p style="text-align: justify;">La désacidification biologique est le résultat de la transformation enzymatique de l'acide L-malique. Levures et bactéries lactiques possèdent un équipement enzymatique, différent à la fois par la nature des produits de la transformation et leur affinité pour le substrat. La fermentation malolactique assurée par les bactéries lactiques est le procédé le plus répandu.</p><p style="text-align: justify;">Sa maîtrise passe par l'utilisation de levains bactériens, dont les plus récents sont ensemencés directement au vin après la fermentation alcoolique. Les résultats des recherches fondamentales sur l'enzyme malolactique permettent aujourd'hui d'envisager la construction de réacteurs enzymatiques et sans doute plus rapidement, le transfert de cette activité enzymatique chez les levures de vinification.</p>
6
Feuillat, François, Jean-René Perrin, René Keller, Danièle Aubert, Pierre Gelhaye, Claude Houssement, Jean Perrin e Pierre Michel. "Simulation expérimentale de « l'expérience tonneau ». Mesure des cinétiques d'imprégnation du liquide dans le bois et d'évaporation de surface". OENO One 28, n. 3 (30 settembre 1994): 227. http://dx.doi.org/10.20870/oeno-one.1994.28.3.1140.
Abstract (sommario):
<p style="text-align: justify;">Un modèle expérimental miniaturisé a été conçu dans le but de simuler "l'interface tonneau". Les cinétiques de l'imprégnation du liquide dans le bois et de l'évaporation de surface ont été mesurées en conditions de cave (15°C ; 90 p. cent HR) pendant 200 jours sur des petits disques à orientation tangentielle (Ø 63 mm; épaisseur 9 mm) à l'aide d'une méthodologie spécifique. Ces résultats expérimentaux ont été obtenus sur 4 espèces traditionnellement employées en tonnellerie (<em>Quercus</em> <em>robur </em>L., <em>Q. petraea</em> Liebl., <em>Castanea sativa</em> Mill., <em>Robinia pseudacacia</em> L.).</p><p style="text-align: justify;">L'analyse des cinétiques d'imprégnation et d'évaporation a permis de caractériser les régimes transitoire et permanent (état d'équilibre). Le régime transitoire est dominé par une forte imprégnation pendant les 40 premiers jours environ, qui décroît ensuite de façon asymptotique. Parallèlement, après un temps de latence appelé "retard à l'évaporation", le flux massique devient progressivement une fonction linéaire du temps. Le régime d'équilibre est atteint lorsque le niveau d'imprégnation de la pièce de bois est maximal et constant soit après 140 jours environ (profil d'humidité d'équilibre). Le fonctionnement en régime stationnaire se caractérise alors par un flux d'imprégnation à la face inteme équivalent au flux d'évaporation à la face exteme.</p><p style="text-align: justify;">Les variations quantitatives des phénomènes sont apparues liées aux conditions de transfert externe (HR de l'air ambiant) et aux conditions de transfert interne (propriétés de la pièce de bois). La comparaison d'échantillons toutes conditions égales par ailleurs a ainsi montré des différences significatives de comportements vraisemblablement liées à la variabilité anatomique du bois (interspécifique, interindividuelle et intraarbre).</p><p style="text-align: justify;">Cette variabilité pourrait avoir des conséquences sur les phénomènes oxydatifs et sur l'extraction des constituants du bois au cours de l'élevage des vins et des eaux-de-vie en fûts.</p>
7
Bouillon, Pierrette, e Katharina Boesefeldt. "Problèmes de traduction automatique dans les sous-langages des bulletins d’avalanches". Meta 37, n. 4 (30 settembre 2002): 635–46. http://dx.doi.org/10.7202/002108ar.
Abstract (sommario):
Résumé Dans cet article, nous décrivons l'état actuel du projet de traduction automatique des bulletins d'avalanches de la Suisse. Après un bref aperçu du projet, nous mettons en évidence les problèmes de traduction, auxquels nous avons été confronté lors du développement du projet et la manière de les résoudre avec ELU, environnement linguistique d'unification. Nous montrerons qu'une collaboration étroite lors de l'écriture des différentes grammaires nous permet généralement d'obtenir une même représentation sémantique dans les différentes langues, laquelle modélise le domaine des avalanches en Suisse. Mais nous maintiendrons aussi qu'un système de transfert est indispensable pour obtenir une traduction de qualité, qui ne provoque pas de modification du style des bulletins.
8
Bara, Florence, e Marie-France Morin. "Est-il nécessaire d’enseigner l’écriture script en première année ? Les effets du style d’écriture sur le lien lecture/écriture". Nouveaux cahiers de la recherche en éducation 12, n. 2 (30 luglio 2013): 149–60. http://dx.doi.org/10.7202/1017456ar.
Abstract (sommario):
Cette étude permet de questionner la tradition du double enseignement des styles d’écriture au Québec, en testant la validité d’un argument couramment avancé, qui suggère que la discordance entre l’écriture cursive et les caractères d’imprimerie nuirait au transfert entre la lecture et l’écriture. Les résultats obtenus auprès d’enfants de 2e année du primaire, ayant appris à écrire en script ou en cursive, ne nous permettent pas d’aller dans le sens de cet argument. En effet, les corrélations entre les performances en lecture et en écriture sont significatives et élevées pour les deux groupes d’enfants, et leurs performances sont similaires. Les apprenants semblent capables d’associer des caractères différents en lecture et en écriture, l’apprentissage de l’écriture cursive en 1re année ne nuirait pas à la lecture.
9
Dorin, Stéphane. "Style du Velours : sociologie du transfert de capital symbolique entre Andy Warhol et le Velvet Underground (1965-1967)". A contrario 3, n. 1 (2005): 45. http://dx.doi.org/10.3917/aco.031.67.
10
Handayani, Sri. "La chanson folklorique enfantine comme media de l’apprentissage interculturel et du transfert des valeurs morales". Digital Press Social Sciences and Humanities 3 (2019): 00040. http://dx.doi.org/10.29037/digitalpress.43313.
Abstract (sommario):
<p class="MsoNormal" style="text-indent:0in">Children's folk song is an example
of cultural products that has several goals in its creation. Aside from
entertaining, this type of song also aims to transfer moral values or character
building to children. Thanks to its moral values, this type of song is a
potential medium as a media of character learning and also intercultural
learning. This article aims to propose a compilation of Javanese children's
folk songs translated into French intended not only for Indonesian learners who
learn French, but also for French speakers who learn Indonesian language. The
research focused on the process of translating the Javanese folk songs into
French. This process is an assimilation of two different cultures by
accentuating on the promotion of the culture of origin through the language.
The future big goal is to make traditional songs better known around the world.
After applying the developmental research approach, seven Javanese children's
folk songs have been translated into French: <i>Gundhul pacul, Padhang mbulan, Menthok-menthok, Dhondhong opo salak,
Sluku-sluku bathok, Lir ilir</i>, and <i>Siji
lor otelu</i>. Each song has its value and also contains cultural elements. A
booklet and a CD containing the translation of Javanese children's folk songs
into French is the final product of this research that could be used in
intercultural learning and at the same time character building</p><p>
</p>
Tesi sul tema "Transfert de style":
1
Mohammed, Omar. "Méthodes d'apprentissage approfondi pour l'extraction et le transfert de style". Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAT035.
Abstract (sommario):
L'un des aspects d'une interface homme-machine réussie (p. ex. interaction homme-robot, chatbots, parole, écriture manuscrite, etc.) est la possibilité d'avoir une interaction personnalisée. Cela affecte l'expérience humaine globale et permet une interaction plus fluide. Actuellement, il y a beaucoup de travaux qui utilisent l'apprentissage machine afin de modéliser de telles interactions. Cependant, ces modèles n'abordent pas la question du comportement personnalisé : ils tentent de faire la moyenne des différents exemples provenant de différentes personnes. L'identification des styles humains (persona) ouvre la possibilité de biaiser la sortie des modèles pour prendre en compte la préférence humaine. Dans cette thèse, nous nous sommes concentrés sur le problème des styles dans le contexte de l'écriture manuscrite.L'objectif de cette thèse est d'étudier ces problèmes de styles, dans le domaine de l'écriture. Nous disposons d'un jeu de données IRONOFF, un jeu de données d'écriture manuscrite en ligne, avec 410 rédacteurs, avec ~25K exemples de dessins en majuscules, minuscules et chiffres. Pour le problème de l'apprentissage par transfert, nous avons utilisé un jeu de données supplémentaire, QuickDraw ! (disponible gratuitement sur Google), un jeu de données de dessin d'esquisses contenant environ 50 millions de dessins sur 345 catégories.Les principales contributions de ma thèse sont :1) Proposer un pipeline de travail pour étudier le problème des styles d'écriture. Il s'agit de proposer une méthodologie, des repères et des paramètres d'évaluation (et de fonder ces paramètres d'évaluation).Nous choisissons le paradigme des modèles génératifs temporels dans l'apprentissage profond afin de générer des dessins et d'évaluer leur proximité/pertinence par rapport aux dessins de vérité voulus/de terrain. Nous avons proposé deux métriques, pour évaluer la courbure et la longueur des dessins générés. Afin d'enraciner ces métis, nous avons proposé de multiples repères - dont nous connaissons le pouvoir relatif à l'avance -, puis vérifié que les mesures respectent effectivement la relation de pouvoir relatif.2) Proposer un cadre pour l'étude et l'extraction des styles, et vérifier son avantage par rapport aux repères proposés précédemment.Nous nous sommes mis d'accord sur l'idée d'utiliser un auto-encodeur conditionné en profondeur pour résumer et extraire les informations de style, sans avoir besoin de nous concentrer sur l'identité de la tâche (puisqu'elle est donnée comme une condition). Nous validons ce cadre par rapport au repère proposé précédemment à l'aide de nos paramètres d'évaluation. Nous visualisons également les styles extraits, ce qui nous permet d'obtenir des résultats passionnants !3) En utilisant le cadre proposé, proposer un moyen de transférer l'information sur les styles entre les différentes tâches, et un protocole afin d'évaluer la qualité du transfert.Nous avons exploité le codeur automatique conditionné profond utilisé précédemment, en extrayant la partie codeur - qui, selon nous, contenait les informations pertinentes sur les styles - et en l'utilisant dans de nouveaux modèles formés sur de nouvelles tâches. Nous testons intensivement ce paradigme sur une gamme différente de tâches, à la fois sur les ensembles de données IRONOFF et QuickDraw!. Nous montrons que nous pouvons transférer avec succès les informations de style entre différentes tâchesOne aspect of a successful human-machine interface (e.g. human-robot interaction, chatbots, speech, handwriting…,etc) is the ability to have a personalized interaction. This affects the overall human experience, and allow for a more fluent interaction. At the moment, there is a lot of work that uses machine learning in order to model such interactions. However, these models do not address the issue of personalized behavior: they try to average over the different examples from different people in the training set. Identifying the human styles (persona) opens the possibility of biasing the models output to take into account the human preference. In this thesis, we focused on the problem of styles in the context of handwriting.Defining and extracting handwriting styles is a challenging problem, since there is no formal definition for those styles (i.e., it is an ill-posed problem). Styles are both social - depending on the writer's training, especially in middle school - and idiosyncratic - depends on the writer's shaping (letter roundness, sharpness…,etc) and force distribution over time. As a consequence, there are no easy/generic metrics to measure the quality of style in a machine behavior.We may want to change the task or adapt to a new person. Collecting data in the human-machine interface domain can be quite expensive and time consuming. Although most of the time the new task has many things in common with the old task, traditional machine learning techniques fail to take advantage of this commonality, leading to a quick degradation in performance. Thus, one of the objectives of my thesis is to study and evaluate the idea of transferring knowledge about the styles between different tasks, within the machine learning paradigm.The objective of my thesis is to study these problems of styles, in the domain of handwriting. Available to us is IRONOFF dataset, an online handwriting datasets, with 410 writers, with ~25K examples of uppercase, lowercase letters and digits drawings. For transfer learning, we used an extra dataset, QuickDraw!, a sketch drawing dataset containing ~50 million drawing over 345 categories.Major contributions of my thesis are:1) Propose a work pipeline to study the problem of styles in handwriting. This involves proposing methodology, benchmarks and evaluation metrics.We choose temporal generative models paradigm in deep learning in order to generate drawings, and evaluate their proximity/relevance to the intended/ground truth drawings. We proposed two metrics, to evaluate the curvature and the length of the generated drawings. In order to ground those metics, we proposed multiple benchmarks - which we know their relative power in advance -, and then verified that the metrics actually respect the relative power relationship.2) Propose a framework to study and extract styles, and verify its advantage against the previously proposed benchmarks.We settled on the idea of using a deep conditioned-autoencoder in order to summarize and extract the style information, without the need to focus on the task identity (since it is given as a condition). We validate this framework to the previously proposed benchmark using our evaluation metrics. We also to visualize on the extracted styles, leading to some exciting outcomes!3) Using the proposed framework, propose a way to transfer the information about styles between different tasks, and a protocol in order to evaluate the quality of transfer.We leveraged the deep conditioned-autoencoder used earlier, by extract the encoder part in it - which we believe had the relevant information about the styles - and use it to in new models trained on new tasks. We extensively test this paradigm over a different range of tasks, on both IRONOFF and QuickDraw! datasets. We show that we can successfully transfer style information between different tasks
2
Cifka, Ondrej. "Deep learning methods for music style transfer". Electronic Thesis or Diss., Institut polytechnique de Paris, 2021. http://www.theses.fr/2021IPPAT029.
Abstract (sommario):
Récemment, les méthodes d'apprentissage profond ont permis d'effectuer des transformations du matériel musical basées sur les données (data-driven). L'objet de cette thèse est le transfert de style musical, dont le but est de transférer de manière automatique le style d'un morceau à un autre. Dans la première partie de ce travail, nous nous concentrons sur les méthodes supervisées pour le transfert de style des accompagnements dans une représentation symbolique, visant à transformer un morceau donné en lui générant un nouvel accompagnement. La méthode proposée est basée sur l'apprentissage supervisé de séquence à séquence à l'aide de réseaux de neurones récurrents (RNN) et s'appuie sur une base de données synthétiques parallèle (alignée par paires) générée à cet effet à l'aide d'un logiciel de génération d'accompagnement existant. Nous proposons ainsi un ensemble de mesures objectives pour évaluer la performance sur cette nouvelle tâche et nous montrons que le système réussit à générer un accompagnement dans le style souhaité tout en suivant la structure harmonique de l'entrée. Dans la deuxième partie, nous étudions une question plus fondamentale : le rôle des encodages positionnels (PE) dans la génération de musique à l'aide des Transformers. Nous proposons l'encodage positionnel stochastique (SPE), un nouveau PE capable de coder des positions relatives et compatible avec une classe récemment proposée de Transformers efficaces. Nous démontrons que le SPE permet, mieux que la méthode conventionnelle (le PE absolu), de modéliser des séquences plus longues que celles rencontrées pendant l'entraînement.Enfin, dans la troisième partie, nous passons de la musique symbolique à l'audio et abordons le problème du transfert de timbre. Plus précisément, nous nous intéressons à transférer le timbre d'un enregistrement audio à un autre, tout en préservant le contenu mélodique et harmonique de ce dernier. Nous présentons une nouvelle méthode pour cette tâche, basée sur une extension de l'autoencodeur variationnel quantifié (VQ-VAE), ainsi qu'une stratégie d'apprentissage auto-supervisé conçue pour obtenir des représentations démêlées du timbre et de la hauteur. Comme dans la première partie, nous concevons un ensemble de métriques objectives pour la tâche. Nous montrons que la méthode proposée est capable de surpasser des méthodes existantesRecently, deep learning methods have enabled transforming musical material in a data-driven manner. The focus of this thesis is on a family of tasks which we refer to as (one-shot) music style transfer, where the goal is to transfer the style of one musical piece or fragment onto another.In the first part of this work, we focus on supervised methods for symbolic music accompaniment style transfer, aiming to transform a given piece by generating a new accompaniment for it in the style of another piece. The method we have developed is based on supervised sequence-to-sequence learning using recurrent neural networks (RNNs) and leverages a synthetic parallel (pairwise aligned) dataset generated for this purpose using existing accompaniment generation software. We propose a set of objective metrics to evaluate the performance on this new task and we show that the system is successful in generating an accompaniment in the desired style while following the harmonic structure of the input.In the second part, we investigate a more basic question: the role of positional encodings (PE) in music generation using Transformers. In particular, we propose stochastic positional encoding (SPE), a novel form of PE capturing relative positions while being compatible with a recently proposed family of efficient Transformers.We demonstrate that SPE allows for better extrapolation beyond the training sequence length than the commonly used absolute PE.Finally, in the third part, we turn from symbolic music to audio and address the problem of timbre transfer. Specifically, we are interested in transferring the timbre of an audio recording of a single musical instrument onto another such recording while preserving the pitch content of the latter. We present a novel method for this task, based on an extension of the vector-quantized variational autoencoder (VQ-VAE), along with a simple self-supervised learning strategy designed to obtain disentangled representations of timbre and pitch. As in the first part, we design a set of objective metrics for the task. We show that the proposed method is able to outperform existing ones
3
Fares, Mireille. "Multimodal Expressive Gesturing With Style". Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS017.
Abstract (sommario):
La génération de gestes expressifs permet aux agents conversationnels animés (ACA) d'articuler un discours d'une manière semblable à celle des humains. Le thème central du manuscrit est d'exploiter et contrôler l'expressivité comportementale des ACA en modélisant le comportement multimodal que les humains utilisent pendant la communication. Le but est (1) d’exploiter la prosodie de la parole, la prosodie visuelle et le langage dans le but de synthétiser des comportements expressifs pour les ACA; (2) de contrôler le style des gestes synthétisés de manière à pouvoir les générer avec le style de n'importe quel locuteur. Nous proposons un modèle de synthèse de gestes faciaux à partir du texte et la parole; et entraîné sur le corpus TEDx que nous avons collecté. Nous proposons ZS-MSTM 1.0, une approche permettant de synthétiser des gestes stylisés du haut du corps à partir du contenu du discours d'un locuteur source et correspondant au style de tout locuteur cible. Il est entraîné sur le corpus PATS qui inclut des données multimodales de locuteurs ayant des styles de comportement différents. Il n'est pas limité aux locuteurs de PATS, et génère des gestes dans le style de n'importe quel nouveau locuteur vu ou non par notre modèle, sans entraînement supplémentaire, ce qui rend notre approche «zero-shot». Le style comportemental est modélisé sur les données multimodales des locuteurs - langage, gestes et parole - et indépendamment de l'identité du locuteur. Nous proposons ZS-MSTM 2.0 pour générer des gestes faciaux stylisés en plus des gestes du haut du corps. Ce dernier est entraîné sur une extension de PATS, qui inclut des actes de dialogue et des repères faciaux en 2DThe generation of expressive gestures allows Embodied Conversational Agents (ECA) to articulate the speech intent and content in a human-like fashion. The central theme of the manuscript is to leverage and control the ECAs’ behavioral expressivity by modelling the complex multimodal behavior that humans employ during communication. The driving forces of the Thesis are twofold: (1) to exploit speech prosody, visual prosody and language with the aim of synthesizing expressive and human-like behaviors for ECAs; (2) to control the style of the synthesized gestures such that we can generate them with the style of any speaker. With these motivations in mind, we first propose a semantically aware and speech-driven facial and head gesture synthesis model trained on the TEDx Corpus which we collected. Then we propose ZS-MSTM 1.0, an approach to synthesize stylized upper-body gestures, driven by the content of a source speaker’s speech and corresponding to the style of any target speakers, seen or unseen by our model. It is trained on PATS Corpus which includes multimodal data of speakers having different behavioral style. ZS-MSTM 1.0 is not limited to PATS speakers, and can generate gestures in the style of any newly coming speaker without further training or fine-tuning, rendering our approach zero-shot. Behavioral style is modelled based on multimodal speakers’ data - language, body gestures, and speech - and independent from the speaker’s identity ("ID"). We additionally propose ZS-MSTM 2.0 to generate stylized facial gestures in addition to the upper-body gestures. We train ZS-MSTM 2.0 on PATS Corpus, which we extended to include dialog acts and 2D facial landmarks
4
Shen, Tianxiao. "Language style transfer". Thesis, Massachusetts Institute of Technology, 2018. http://hdl.handle.net/1721.1/117822.
Abstract (sommario):
Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 41-45).
This thesis studies style transfer on the basis of non-parallel text. This is an instance of a broad family of problems including machine translation, decipherment, and attribute modication. The key challenge is to separate the content from style in an unsupervised manner. We assume a shared latent content distribution across different text corpora, and propose a method that leverages refined alignment of latent representations to perform style transfer. The transferred sentences from one style should match example sentences from the other style as a population. To demonstrate the flexibility of the proposed model, we test it on three tasks: sentiment modication, decipherment of word substitution ciphers, and word order recovery. In both automatic and human evaluation our method achieves strong performance.
by Tianxiao Shen.
S.M.
5
Hart, David Marvin. "Light-Field Style Transfer". BYU ScholarsArchive, 2019. https://scholarsarchive.byu.edu/etd/7763.
Abstract (sommario):
For many years, light fields have been a unique way of capturing a scene. By using a particular set of optics, a light field camera is able to, in a single moment, take images of the same scene from multiple perspectives. These perspectives can be used to calculate the scene geometry and allow for effects not possible with standard photographs, such as refocus and the creation of novel views.Neural style transfer is the process of training a neural network to render photographs in the style of a particular painting or piece of art. This is a simple process for a single photograph, but naively applying style transfer to each view in a light field generates inconsistencies in coloring between views. Because of these inconsistencies, common light field effects break down.We propose a style transfer method for light fields that maintains consistencies between different views of the scene. This is done by using warping techniques based on the depth estimation of the scene. These warped images are then used to compare areas of similarity between views and incorporate differences into the loss function of the style transfer network. Additionally, this is done in a post-training fashion, which removes the need for a light field training set.
6
Graffieti, Gabriele. "Style Transfer with Generative Adversarial Networks". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/17015/.
Abstract (sommario):
This dissertation is focused on trying to use concepts from style transfer and image-to-image translation to address the problem of defogging. Defogging (or dehazing) is the ability to remove fog from an image, restoring it as if the photograph was taken during optimal weather conditions. The task of defogging is of particular interest in many fields, such as surveillance or self driving cars.
In this thesis an unpaired approach to defogging is adopted, trying to translate a foggy image to the correspondent clear picture without having pairs of foggy and ground truth haze-free images during training. This approach is particularly significant, due to the difficult of gathering an image collection of exactly the same scenes with and without fog.
Many of the models and techniques used in this dissertation already existed in literature, but they are extremely difficult to train, and often it is highly problematic to obtain the desired behavior. Our contribute was a systematic implementative and experimental activity, conducted with the aim of attaining a comprehensive understanding of how these models work, and the role of datasets and training procedures in the final results. We also analyzed metrics and evaluation strategies, in order to seek to assess the quality of the presented model in the most correct and appropriate manner.
First, the feasibility of an unpaired approach to defogging was analyzed, using the cycleGAN model. Then, the base model was enhanced with a cycle perceptual loss, inspired by style transfer techniques. Next, the role of the training set was investigated, showing that improving the quality of data is at least as important as the utilization of more powerful models. Finally, our approach is compared with state-of-the art defogging methods, showing that the quality of our results is in line with preexisting approaches, even if our model was trained using unpaired data.
7
Matthews, Nicholas (Nicholas J. ). "Evaluating style transfer in natural language". Thesis, Massachusetts Institute of Technology, 2018. http://hdl.handle.net/1721.1/119734.
Abstract (sommario):
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018.This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 46-47).
Style transfer is an active area of research growing in popularity in the Natural Language setting. The goal of this thesis is present a comprehensive review of style transfer tasks used to date, analyze these tasks, and delineate important properties and candidate tasks for future methods researchers. Several challenges still exist, including the difficulty of distinguishing between content and style in a sentence. While some state of the art models attempt to overcome this problem, even tasks as simple as sentiment transfer are still non-trivial. Problems of granularity, transferability, and distinguishability have yet to be solved. I provide a comprehensive analysis of the popular sentiment transfer task along with a number of metrics that highlight its shortcomings. Finally, I introduce possible new tasks for consideration, news outlet style transfer and non-parallel error correction, and provide similar analysis for the feasibility of using these tasks as style transfer baselines.
by Nicholas Matthews.
M. Eng.
8
Battilana, Pietro. "Convolutional Neural Networks for Image Style Transfer". Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/16770/.
Abstract (sommario):
In this thesis we will use deep learning tools to tackle an interesting and complex problem of image processing called style transfer. Given a content image and a style image as inputs, the aim is to create a new image preserving the global structure of the content image but showing the artistic patterns of the style image.
Before the renaissance of Arti�cial Neural Networks, early work in the �field called texture synthesis, only transferred limited and repeatitive geometric patterns of textures. Due to the avaibility of large amounts of data and cheap computational resources in the last decade Convolutional Neural Networks and Graphics Processing Units have been at the core of a paradigm shift in computer vision research. In the seminal work of Neural Style Transfer, Gatys et al. consistently disentangled style and content
from different images to combine them in artistic compositions of high perceptual quality. This was done using the image representation derived from Convolutional Neural Networks trained for large-scale object recognition, which make high level image informations explicit. In this thesis, inspired by the work of Li et al., we build an efficient neural style transfer method able to
transfer arbitrary styles. Existing optimisation-based methods (Gatys et al.), produce visually pleasing results but are limited
because of the time consuming optimisation procedure. More
recent feedforward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen
styles. The key ingredients of our approach are a Convolutional
Autoencoder and a pair of feature transforms, Whitening and Coloring, reflecting a direct matching of feature covariance of the content image to the given style image. The algorithm allows us to produce images of high perceptual quality that combine the content of an arbitrary photograph with the appearance of arbitrary well known artworks.
9
Shih, YiChang. "Data-driven photographic style using local transfer". Thesis, Massachusetts Institute of Technology, 2015. http://hdl.handle.net/1721.1/99846.
Abstract (sommario):
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2015.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 139-154).
After taking pictures, photographers often seek to convey their unique moods by altering the style of their photographs, which can involve meticulous contrast management, lighting, dodging, and burning. In this sense, not only are advanced photographers concerned about their pictures' styles; casual photographers who take pictures with cellphone cameras also process their pictures using built-in applications to adjust the image's luminance, coloring, and details. In general, photographers who stylize pictures give them new, different visual appearances, while also preserving the original content. In this context, we investigate problems with novel image stylization, including reproducing the precise time-of-day where the lighting and atmosphere can make a landscape glow, and making a portrait style resemble that created by a renowned photographer. Given an already captured image, however, automatically achieving given styles is challenging. In fact, changing the appearance in a photograph to mimic another time-of-day requires the analysis and modeling of complex 3-D physical light interactions in the scene, while reproducing a portrait photographer's unique style require computers to acquire artistic tastes and a glimpse of the artist's creative process. In this dissertation, we sidestep these Al-complete problems to instead leverage the power of data. We exploit an image database consisting of time-lapse data describing variations in scene appearance during the course of an entire day, and stylish portraits that are already deliberately processed by artists. To leverage these data, we present new algorithms that put input images in dense and local correspondence with examples. In our first method, we change the time-of-day with a single image as the input, which we put in correspondence with a reference time-lapse video. We then extract the local appearance transformations between different frames of the reference, and apply them to the input. In our second method, we transfer the style of a portrait onto a new input by way of local and multi-scale transformations. We demonstrate our methods on public datasets and a large set of photos downloaded from the Internet. We show that we can successfully handle lightings at different times of day and styles by a variety of different artists.
by YiChang Shih.
Ph. D.
10
Tao, Joakim, e David Thimrén. "Smoothening of Software documentation : comparing a self-made sequence to sequence model to a pre-trained model GPT-2". Thesis, Linköpings universitet, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-178186.
Abstract (sommario):
This thesis was done in collaboration with Ericsson AB with the goal of researching the possibility of creating a machine learning model that can transfer the style of a text into another arbitrary style depending on the data used. This had the purpose of making their technical documentation appear to have been written with one cohesive style for a better reading experience. Two approaches to solve this task were tested, the first one was to implement an encoder-decoder model from scratch, and the second was to use the pre-trained GPT-2 model created by a team from OpenAI and fine-tune the model on the specific task. Both of these models were trained on data provided by Ericsson, sentences were extracted from their documentation. To evaluate the models training loss, test sentences, and BLEU scores were used and these were compared to each other and with other state-of-the-art models. The models did not succeed in transforming text into a general technical documentation style but a good understanding of what would need to be improved and adjusted to improve the results were obtained.This thesis was presented on June 22, 2021, the presentation was done online on Microsoft teams.
Libri sul tema "Transfert de style":
1
Monahan, Gretta. Style and the successful girl: Transform your look, transform your life. New York: Gotham Books, 2013.
2
Holding, Jocelyn Kerr. Stencil style: Ideas and projects to transform your home. London: Ward Lock, 1995.
3
Riley, Lesley. Creative image transfer--any artist, any style, any surface: 16 new mixed-media projects using transfer artist paper. Lafayette, CA: C&T Publishing, 2014.
4
Koch, Amy Tara. Bump it up: Transform your pregnancy into the ultimate style statement. New York: Ballantine Books, 2010.
5
H, Brown John. How to run your business so you can leave it in style. New York, NY: Amacom, American Management Association, 1990.
6
H, Brown John. The completely revised how to run your business so you can leave it in style. 2a ed. [Denver, Colo.]: Business Enterprise Press, 1997.
7
Rosenberg, Merrick. Taking flight!: Master the four behavioral styles and transform your career, your relationships-- your life. Upper Saddle River, N.J: FT Press, 2013.
8
Hughes, Mike. Tweak to transform: Improving teaching : a practical handbook for school leaders. Stafford: Network Educational Press, 2002.
9
Zhang, Ming. Ji ceng zhi li mo shi zhuan xing: Yang Cun ge an yan jiu = Administration style transfer at the grass-roots : a case study of Yang Village. 8a ed. Beijing Shi: She hui ke xue wen xian chu ban she, 2008.
10
Zhang, Ming. Ji ceng zhi li mo shi zhuan xing: Yang Cun ge an yan jiu = Administration style transfer at the grass-roots : a case study of Yang Village. 8a ed. Beijing Shi: She hui ke xue wen xian chu ban she, 2008.
Capitoli di libri sul tema "Transfert de style":
1
Sarang, Poornachandra. "Style Transfer". In Artificial Neural Networks with TensorFlow 2, 577–611. Berkeley, CA: Apress, 2020. http://dx.doi.org/10.1007/978-1-4842-6150-7_12.
2
Liu, Shiguang. "Style Transfer". In Synthesis Lectures on Visual Computing: Computer Graphics, Animation, Computational Photography and Imaging, 55–64. Cham: Springer International Publishing, 2023. http://dx.doi.org/10.1007/978-3-031-26030-8_6.
3
Wutt, Karl. "Stile". In Edition Transfer, 54–57. Vienna: Springer Vienna, 2010. http://dx.doi.org/10.1007/978-3-211-99154-1_7.
4
Kim, Sunnie S. Y., Nicholas Kolkin, Jason Salavon e Gregory Shakhnarovich. "Deformable Style Transfer". In Computer Vision – ECCV 2020, 246–61. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-58574-7_15.
5
Chen, Dongdong, Lu Yuan e Gang Hua. "Deep Style Transfer". In Computer Vision, 1–8. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-03243-2_863-1.
6
Dana, Kristin J. "Texture Style Transfer". In Computational Texture and Patterns, 47–50. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-031-01823-7_6.
7
Paper, David. "Fast Style Transfer". In State-of-the-Art Deep Learning Models in TensorFlow, 295–319. Berkeley, CA: Apress, 2021. http://dx.doi.org/10.1007/978-1-4842-7341-8_12.
8
Chen, Dongdong, Lu Yuan e Gang Hua. "Deep Style Transfer". In Computer Vision, 269–76. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-63416-2_863.
9
Teoh, Teik Toe, e Zheng Rong. "Neural Style Transfer". In Machine Learning: Foundations, Methodologies, and Applications, 303–19. Singapore: Springer Singapore, 2022. http://dx.doi.org/10.1007/978-981-16-8615-3_19.
10
McAllister, Tyler, e Björn Gambäck. "Music Style Transfer Using Constant-Q Transform Spectrograms". In Artificial Intelligence in Music, Sound, Art and Design, 195–211. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-03789-4_13.
Atti di convegni sul tema "Transfert de style":
1
Schaldenbrand, Peter, Zhixuan Liu e Jean Oh. "StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Translation". In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/688.
Abstract (sommario):
Generating images that fit a given text description using machine learning has improved greatly with the release of technologies such as the CLIP image-text encoder model; however, current methods lack artistic control of the style of image to be generated. We present an approach for generating styled drawings for a given text description where a user can specify a desired drawing style using a sample image. Inspired by a theory in art that style and content are generally inseparable during the creative process, we propose a coupled approach, known here as StyleCLIPDraw, whereby the drawing is generated by optimizing for style and content simultaneously throughout the process as opposed to applying style transfer after creating content in a sequence. Based on human evaluation, the styles of images generated by StyleCLIPDraw are strongly preferred to those by the sequential approach. Although the quality of content generation degrades for certain styles, overall considering both content and style, StyleCLIPDraw is found far more preferred, indicating the importance of style, look, and feel of machine generated images to people as well as indicating that style is coupled in the drawing process itself. Our code, a demonstration, and style evaluation data are publicly available.
2
Ponamaryov, Valeriy, e Victor Kitov. "Image Style Transfer With a Group of Similar Styles". In 33rd International Conference on Computer Graphics and Vision. Keldysh Institute of Applied Mathematics, 2023. http://dx.doi.org/10.20948/graphicon-2023-565-571.
Abstract (sommario):
Image style transfer is a widely used applied task of automatic redrawing of the source image (content) in the style of another image (setting the target style). Traditional style transfer methods provide only a single stylization result. If the user does not like it, for example, due to artifacts that appear during styling, then he has to choose another style. The paper proposes a modification of the styling algorithm, which gives a variety of styling results with one style, and also improves the average quality of styling by using not only style information from the original style image, but also information from images that have a similar style.
3
Chen, Jiafu, Boyan Ji, Zhanjie Zhang, Tianyi Chu, Zhiwen Zuo, Lei Zhao, Wei Xing e Dongming Lu. "TeSTNeRF: Text-Driven 3D Style Transfer via Cross-Modal Learning". In Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}. California: International Joint Conferences on Artificial Intelligence Organization, 2023. http://dx.doi.org/10.24963/ijcai.2023/642.
Abstract (sommario):
Text-driven 3D style transfer aims at stylizing a scene according to the text and generating arbitrary novel views with consistency. Simply combining image/video style transfer methods and novel view synthesis methods results in flickering when changing viewpoints, while existing 3D style transfer methods learn styles from images instead of texts. To address this problem, we for the first time design an efficient text-driven model for 3D style transfer, named TeSTNeRF, to stylize the scene using texts via cross-modal learning: we leverage an advanced text encoder to embed the texts in order to control 3D style transfer and align the input text and output stylized images in latent space. Furthermore, to obtain better visual results, we introduce style supervision, learning feature statistics from style images and utilizing 2D stylization results to rectify abrupt color spill. Extensive experiments demonstrate that TeSTNeRF significantly outperforms existing methods and provides a new way to guide 3D style transfer.
4
Yi, Xiaoyuan, Zhenghao Liu, Wenhao Li e Maosong Sun. "Text Style Transfer via Learning Style Instance Supported Latent Space". In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. California: International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/526.
Abstract (sommario):
Text style transfer pursues altering the style of a sentence while remaining its main content unchanged. Due to the lack of parallel corpora, most recent work focuses on unsupervised methods and has achieved noticeable progress. Nonetheless, the intractability of completely disentangling content from style for text leads to a contradiction of content preservation and style transfer accuracy. To address this problem, we propose a style instance supported method, StyIns. Instead of representing styles with embeddings or latent variables learned from single sentences, our model leverages the generative flow technique to extract underlying stylistic properties from multiple instances of each style, which form a more discriminative and expressive latent style space. By combining such a space with the attention-based structure, our model can better maintain the content and simultaneously achieve high transfer accuracy. Furthermore, the proposed method can be flexibly extended to semi-supervised learning so as to utilize available limited paired data. Experiments on three transfer tasks, sentiment modification, formality rephrasing, and poeticness generation, show that StyIns obtains a better balance between content and style, outperforming several recent baselines.
5
Zuo, Zhiwen, Lei Zhao, Shuobin Lian, Haibo Chen, Zhizhong Wang, Ailin Li, Wei Xing e Dongming Lu. "Style Fader Generative Adversarial Networks for Style Degree Controllable Artistic Style Transfer". In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/693.
Abstract (sommario):
Artistic style transfer is the task of synthesizing content images with learned artistic styles. Recent studies have shown the potential of Generative Adversarial Networks (GANs) for producing artistically rich stylizations. Despite the promising results, they usually fail to control the generated images' style degree, which is inflexible and limits their applicability for practical use. To address the issue, in this paper, we propose a novel method that for the first time allows adjusting the style degree for existing GAN-based artistic style transfer frameworks in real time after training. Our method introduces two novel modules into existing GAN-based artistic style transfer frameworks: a Style Scaling Injection (SSI) module and a Style Degree Interpretation (SDI) module. The SSI module accepts the value of Style Degree Factor (SDF) as the input and outputs parameters that scale the feature activations in existing models, offering control signals to alter the style degrees of the stylizations. And the SDI module interprets the output probabilities of a multi-scale content-style binary classifier as the style degrees, providing a mechanism to parameterize the style degree of the stylizations. Moreover, we show that after training our method can enable existing GAN-based frameworks to produce over-stylizations. The proposed method can facilitate many existing GAN-based artistic style transfer frameworks with marginal extra training overheads and modifications. Extensive qualitative evaluations on two typical GAN-based style transfer models demonstrate the effectiveness of the proposed method for gaining style degree control for them.
6
Lu, Haofei, e Zhizhong Wang. "Universal Video Style Transfer via Crystallization, Separation, and Blending". In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/687.
Abstract (sommario):
Universal video style transfer aims to migrate arbitrary styles to input videos. However, how to maintain the temporal consistency of videos while achieving high-quality arbitrary style transfer is still a hard nut to crack. To resolve this dilemma, in this paper, we propose the CSBNet which involves three key modules: 1) the Crystallization (Cr) Module that generates several orthogonal crystal nuclei, representing hierarchical stability-aware content and style components, from raw VGG features; 2) the Separation (Sp) Module that separates these crystal nuclei to generate the stability-enhanced content and style features; 3) the Blending (Bd) Module to cross-blend these stability-enhanced content and style features, producing more stable and higher-quality stylized videos. Moreover, we also introduce a new pair of component enhancement losses to improve network performance. Extensive qualitative and quantitative experiments are conducted to demonstrate the effectiveness and superiority of our CSBNet. Compared with the state-of-the-art models, it not only produces temporally more consistent and stable results for arbitrary videos but also achieves higher-quality stylizations for arbitrary images.
7
Wang, Zhizhong, Lei Zhao, Haibo Chen, Zhiwen Zuo, Ailin Li, Wei Xing e Dongming Lu. "DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfer". In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/690.
Abstract (sommario):
Gram-based and patch-based approaches are two important research lines of style transfer. Recent diversified Gram-based methods have been able to produce multiple and diverse stylized outputs for the same content and style images. However, as another widespread research interest, the diversity of patch-based methods remains challenging due to the stereotyped style swapping process based on nearest patch matching. To resolve this dilemma, in this paper, we dive into the crux of existing patch-based methods and propose a universal and efficient module, termed DivSwapper, for diversified patch-based arbitrary style transfer. The key insight is to use an essential intuition that neural patches with higher activation values could contribute more to diversity. Our DivSwapper is plug-and-play and can be easily integrated into existing patch-based and Gram-based methods to generate diverse results for arbitrary styles. We conduct theoretical analyses and extensive experiments to demonstrate the effectiveness of our method, and compared with state-of-the-art algorithms, it shows superiority in diversity, quality, and efficiency.
8
Yin, Di, Shujian Huang, Xin-Yu Dai e Jiajun Chen. "Utilizing Non-Parallel Text for Style Transfer by Making Partial Comparisons". In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/747.
Abstract (sommario):
Text style transfer aims to rephrase a given sentence into a different style without changing its original content. Since parallel corpora (i.e. sentence pairs with the same content but different styles) are usually unavailable, most previous works solely guide the transfer process with distributional information, i.e. using style-related classifiers or language models, which neglect the correspondence of instances, leading to poor transfer performance, especially for the content preservation. In this paper, we propose making partial comparisons to explicitly model the content and style correspondence of instances, respectively. To train the partial comparators, we propose methods to extract partial-parallel training instances automatically from the non-parallel data, and to further enhance the training process by using data augmentation. We perform experiments that compare our method to other existing approaches on two review datasets. Both automatic and manual evaluations show that our approach can significantly improve the performance of existing adversarial methods, and outperforms most state-of-the-art models. Our code and data will be available on Github.
9
Srivastava, Hardik, Sneha Sunil e K. Shantha Kumari. "Neural Text Style Transfer with Custom Language Styles for Personalized Communication Systems". In 2022 International Conference on Knowledge Engineering and Communication Systems (ICKECS). IEEE, 2022. http://dx.doi.org/10.1109/ickecs56523.2022.10059789.
10
Semmo, Amir, Tobias Isenberg e Jürgen Döllner. "Neural style transfer". In the Symposium. New York, New York, USA: ACM Press, 2017. http://dx.doi.org/10.1145/3092919.3092920.
Rapporti di organizzazioni sul tema "Transfert de style":
1
Stock, Gregory J. An Investigation of Applications of Neural Style Transfer to Forensic Footwear Comparison. Gaithersburg, MD: National Institute of Standards and Technology, 2023. http://dx.doi.org/10.6028/nist.gcr.23-040.
2
Stock, Gregory. An Investigation of Applications of Neural Style Transfer to Forensic Footwear Comparison. Gaithersburg, MD: National Institute of Standards and Technology, 2023. http://dx.doi.org/10.6028/nist.ir.8460.
3
Eyal, Yoram, e Sheila McCormick. Molecular Mechanisms of Pollen-Pistil Interactions in Interspecific Crossing Barriers in the Tomato Family. United States Department of Agriculture, maggio 2000. http://dx.doi.org/10.32747/2000.7573076.bard.
Abstract (sommario):
During the evolutionary process of speciation in plants, naturally occurring barriers to reproduction have developed that affect the transfer of genes within and between related species. These barriers can occur at several different levels beginning with pollination-barriers and ending with hybrid-breakdown. The interaction between pollen and pistils presents one of the major barriers to intra- and inter-specific crosses and is the focus of this research project. Our long-term goal in this research proposal was defined to resolve questions on recognition and communication during pollen-pistil interactions in the extended tomato family. In this context, this work was initiated and planned to study the potential involvement of tomato pollen-specific receptor-like kinases (RLK's) in the interaction between pollen and pistils. By special permission from BARD the objectives of this research were extended to include studies on pollen-pistil interactions and pollination barriers in horticultural crops with an emphasis on citrus. Functional characterization of 2 pollen-specific RLK's from tomato was carried out. The data shows that both encode functional kinases that were active as recombinant proteins. One of the kinases was shown to accumulate mainly after pollen germination and to be phosphorylated in-vitro in pollen membranes as well as in-vivo. The presence of style extract resulted in dephosphorylation of the RLK, although no species specificity was observed. This data implies a role for at least one RLK in pollination events following pollen germination. However, a transgenic plant analysis of the RLK's comprising overexpression, dominant-negative and anti-sense constructs failed to provide answers on their role in pollination. While genetic effects on some of the plants were observed in both the Israeli and American labs, no clear functional answers were obtained. An alternative approach to addressing function was pursued by screening for an artificial ligand for the receptor domain using a peptide phage display library. An enriched peptide sequence was obtained and will be used to design a peptide-ligand to be tested for its effect o pollen germination and tube growth. Self-incompatibility (SI) in citrus was studied on 3 varieties of pummelo. SI was observed using fluorescence microscopy in each of the 3 varieties and compatibility relations between varieties was determined. An initial screen for an S-RNase SI mechanism yielded only a cDNA homologous to the group of S-like RNases, suggesting that SI results from an as yet unknown mechanism. 2D gel electrophoresis was applied to compare pollen and style profiles of different compatibility groups. A "polymorphic" protein band from style extracts was observed, isolated and micro-sequenced. Degenerate primers designed based on the peptide sequence date will be used to isolate the relevant genes i order to study their potential involvement in SI. A study on SI in the apple cultivar Top red was initiated. SI was found, as previously shown, to be complete thus requiring a compatible pollinator variety. A new S-RNase allele was discovered fro Top red styles and was found to be highly homologous to pear S-RNases, suggesting that evolution of these genes pre-dated speciation into apples and pears but not to other Rosaceae species. The new allele provides molecular-genetic tools to determine potential pollinators for the variety Top red as well as a tool to break-down SI in this important variety.
4
Law, Edward, Samuel Gan-Mor, Hazel Wetzstein e Dan Eisikowitch. Electrostatic Processes Underlying Natural and Mechanized Transfer of Pollen. United States Department of Agriculture, maggio 1998. http://dx.doi.org/10.32747/1998.7613035.bard.
Abstract (sommario):
The project objective was to more fully understand how the motion of pollen grains may be controlled by electrostatic forces, and to develop a reliable mechanized pollination system based upon sound electrostatic and aerodynamic principles. Theoretical and experimental analyses and computer simulation methods which investigated electrostatic aspects of natural pollen transfer by insects found that: a) actively flying honeybees accumulate ~ 23 pC average charge (93 pC max.) which elevates their bodies to ~ 47 V likely by triboelectrification, inducing ~ 10 fC of opposite charge onto nearby pollen grains, and overcoming their typically 0.3-3.9 nN detachment force resulting in non-contact electrostatic pollen transfer across a 5 mm or greater air gap from anther-to-bee, thus providing a theoretical basis for earlier experimental observations and "buzz pollination" events; b) charge-relaxation characteristics measured for flower structural components (viz., 3 ns and 25 ns time constants, respectively, for the stigma-style vs. waxy petal surfaces) ensure them to be electrically appropriate targets for electrodeposition of charged pollen grains but not differing sufficiently to facilitate electrodynamic focusing onto the stigma; c) conventional electrostatic focusing beneficially concentrates pollen-deposition electric fields onto the pistill tip by 3-fold as compared to that onto underlying flower structures; and d) pollen viability is adequately maintained following exposure to particulate charging/management fields exceeding 2 MV/m. Laboratory- and field-scale processes/prototype machines for electrostatic application of pollen were successfully developed to dispense pollen in both a dry-powder phase and in a liquid-carried phase utilizing corona, triboelectric, and induction particulate-charging methods; pollen-charge levels attained (~ 1-10 mC/kg) provide pollen-deposition forces 10-, 77-, and 100-fold greater than gravity, respectively, for such charged pollen grains subjected to a 1 kV/cm electric field. Lab and field evaluations have documented charged vs. ukncharged pollen deposition to be significantly (a = 0.01-0.05) increased by 3.9-5.6 times. Orchard trials showed initial fruit set on branches individually treated with electrostatically applied pollen to typically increase up to ~ 2-fold vs. uncharged pollen applications; however, whole-tree applications have not significantly shown similar levels of benefit and corrective measures continue. Project results thus contribute important basic knowledge and applied electrostatics technology which will provide agriculture with alternative/supplemental mechanized pollination systems as tranditional pollen-transfer vectors are further endangered by natural and man-fade factors.
5
Xu, Jin-Rong, e Amir Sharon. Comparative studies of fungal pathogeneses in two hemibiotrophs: Magnaporthe grisea and Colletotrichum gloeosporioides. United States Department of Agriculture, maggio 2008. http://dx.doi.org/10.32747/2008.7695585.bard.
Abstract (sommario):
Plant pathogenic fungi have various life styles and different plant infection strategies. Hemibiotrophs like Magnaporthe grisea and Colletotrichum species develop specialized structures during plant infection. The goal of this study was to identify, characterize, and compare genes required for plant infection in M. grisea and C. gloeosporioides. Specific objectives are to: 1) further characterize genes identified in the preliminary studies of C. gloeosporioides and M. grisea;2) identify and characterize additional fungal genes tagged by GFP; and 3) identify in planta growth and appressorium-specific genes by subtractive hybridization and transcript profiling by the LongSAGE method. In this study, the PI and Co-PI collaborated closely on studies in M. grisea and C. gloeosporioides. In M. grisea, REMI and ATMT were used to transform the wildtype with promoter-less EGFP constructs. A total of 28 mutants defective in different plant infection processes or expressing EGFP during plant infection were identified. Genes disrupted in five selected mutants have been identified, including MG03295 that encodes a putative Rho GTPase. In transformant L1320, the transforming vector was inserted in the MIRI gene that encodes a nuclear protein. The expression of MIRI was highly induced during infection. Deletion and site-directed mutagenesis analyses were used to identify the promoter regions and elements that were essential for induced in planta expression of MIRI. This was the first detailed characterization of the promoter of an in planta gene in M. grisea and the MIRI promoter can be used to monitor infectious growth. In addition, the Agilent whole-genome array of M. grisea was used for microarray analyses with RNA samples from appressoria formed by the wild-type shain and the pmkl and mstl2 mutants. Over 200 genes were downregulated in the mst I 2 and pmkl mutants. Some of them are putative transcription factors that may regulate appressorium formation and infectious hyphal growth. In C. gloeosporioides, various REMI mutants showing different pathogenic behavior were identified and characterized. Mutants N3736 had a single insertion and was hyper-virulent. The gene disrupted in mutant3736 (named CgFMOI) encodes a FAD-dependent monooxygenase. Expression analyses linked the expression of the CgFMOI gene with the necrotrophic phase of fungal infection, and also suggest that expression of CgFMOl is unnecessary for the first stages of infection and for biotrophy establishment. All CgFMOl-silenced mutants had reduced virulence. In REMI mutant N159, the tagged gene encodes a putative copper transporter that is homologue of S. cerevisiae CTR2. In yeast, Ctr2 is a vacuolar transporter for moving copper from the vacuole to the cytoplasm. The gene was therefore termed CgCTR2. In addition to characterization of CgCTR2, we also conducted comparative analyses in M. grisea. The M. grisea CgCTR-2 homolog was isolated, knockout strains were generated and characterized and the M. grisea was used to complement the Nl 59 C. gloeosporioides mutant. Overall, we have accomplished most of proposed experiments and are in the process of organizing and publishing other data generated in this project. For objective 3, we used the microarray analysis approach. Several genes identified in this study are novel fungal virulence factors. They have the potential to be used as targets for developing more specific or effective fungicides. In the long run, comparative studies of fungal genes, such as our CgCTR2 work, may lead to better disease control strategies.