Sommaire
Littérature scientifique sur le sujet « Transformateur de vision »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les listes thématiques d’articles de revues, de livres, de thèses, de rapports de conférences et d’autres sources académiques sur le sujet « Transformateur de vision ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Articles de revues sur le sujet "Transformateur de vision"
PACAL, Ishak. « A Vision Transformer-based Approach for Automatic COVID-19 Diagnosis on Chest X-ray Images ». Journal of the Institute of Science and Technology 13, no 2 (1 juin 2023) : 778–91. http://dx.doi.org/10.21597/jist.1225156.
Texte intégralBODIN, L., G. BOLET, M. GARCIA, H. GARREAU, C. LARZUL et I. DAVID. « Robustesse et canalisation : vision de généticiens ». INRAE Productions Animales 23, no 1 (8 février 2010) : 11–22. http://dx.doi.org/10.20870/productions-animales.2010.23.1.3281.
Texte intégralBingle, P. W., et J. J. Van der Walt. « Prediking : eskatologiese transformator en alarmsinjaal ». In die Skriflig/In Luce Verbi 25, no 3 (25 juin 1991). http://dx.doi.org/10.4102/ids.v25i3.1383.
Texte intégralThèses sur le sujet "Transformateur de vision"
González, Romero Lilián Ysabel. « Une dimension thérapeutique de l’art d’après une vision esthétique : une approche du pouvoir transformateur de l'art ». Paris 8, 2013. http://octaviana.fr/document/171317696#?c=0&m=0&s=0&cv=0.
Texte intégralArt leads to a kind of revelation which allows us to rediscover the world but above all to rediscover the individual. This rediscovery and the wonder Art brings about call on two central aspects: Subjectivity and Expressiveness. This could be the cause of a certain Art’s transforming power as a space of revelation and expressiveness that contributes, moreover, to meet oneself, the other and the world. We consider that this transforming ability of Art constitutes, precisely, a foundation of its therapeutical power. The main purpose of this investigation is to create an approach to this therapeutical power of Art. The interest of this study lies on the fact that we start from an aesthetical point of view. The aesthetical approach of therapeutics in Art dismisses a psychological and psychoanalytical angle - that is a clinical view - from two aspects: the first one is the consideration of Art as a phenomenon per se instead of a means of psychological and psychoanalytical therapy; the second one resides in the emphasis of expressiveness. The aesthetical approach of Art therapeutics finds its justification, sense and raison d’être within a society and humanity that have become subjects of a lifestyle which has been imposed by a complexe dominant system. This system is characterised by a serious ecological crisis mainly resulting from the destructive action of what Felix Guattari calls « Global Capitalism » (CMI : Capitalisme Mondial Intégral)
Zhang, Yujing. « Deep learning-assisted video list decoding in error-prone video transmission systems ». Electronic Thesis or Diss., Valenciennes, Université Polytechnique Hauts-de-France, 2024. http://www.theses.fr/2024UPHF0028.
Texte intégralIn recent years, video applications have developed rapidly. At the same time, the video quality experience has improved considerably with the advent of HD video and the emergence of 4K content. As a result, video streams tend to represent a larger amount of data. To reduce the size of these video streams, new video compression solutions such as HEVC have been developed.However, transmission errors that may occur over networks can cause unwanted visual artifacts that significantly degrade the user experience. Various approaches have been proposed in the literature to find efficient and low-complexity solutions to repair video packets containing binary errors, thus avoiding costly retransmission that is incompatible with the low latency constraints of many emerging applications (immersive video, tele-operation). Error correction based on cyclic redundancy check (CRC) is a promising approach that uses readily available information without throughput overhead. However, in practice it can only correct a limited number of errors. Depending on the generating polynomial used, the size of the packets and the maximum number of errors considered, this method can lead not to a single corrected packet but rather to a list of possibly corrected packets. In this case, list decoding becomes relevant in combination with CRC-based error correction as well as methods exploiting information on the reliability of the received bits. However, this has disadvantages in terms of selection of candidate videos. Following the generation of ranked candidates during the state-of-the-art list decoding process, the final selection often considers the first valid candidate in the final list as the reconstructed video. However, this simple selection is arbitrary and not optimal, the candidate video sequence at the top of the list is not necessarily the one which presents the best visual quality. It is therefore necessary to develop a new method to automatically select the video with the highest quality from the list of candidates.We propose to select the best candidate based on the visual quality determined by a deep learning (DL) system. Considering that distortions will be assessed on each frame, we consider image quality assessment rather than video quality assessment. More specifically, each candidate undergoes processing by a reference-free image quality assessment (IQA) method based on deep learning to obtain a score. Subsequently, the system selects the candidate with the highest IQA score. To do this, our system evaluates the quality of videos subject to transmission errors without eliminating lost packets or concealing lost regions. Distortions caused by transmission errors differ from those accounted for by traditional visual quality measures, which typically deal with global, uniform image distortions. Thus, these metrics fail to distinguish the repaired version from different corrupted video versions when local, non-uniform errors occur. Our approach revisits and optimizes the classic list decoding technique by associating it with a CNN architecture first, then with a Transformer to evaluate the visual quality and identify the best candidate. It is unprecedented and offers excellent performance. In particular, we show that when transmission errors occur within an intra frame, our CNN and Transformer-based architectures achieve 100% decision accuracy. For errors in an inter frame, the accuracy is 93% and 95%, respectively
Samuelsson, Robert. « Karlstad Vision 100 000 och dess implementering för Karlstads Elnät AB 2011-2015 ». Thesis, Karlstads universitet, Fakulteten för teknik- och naturvetenskap, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-8427.
Texte intégralKarlstads Kommun har en vision att få en befolkningsmängd på 100 000 invånare. För att få en bild av det framtida energibehovet bör man först skapa sig en bild över dagens elbehov. Detta sker på två sätt, först genom att summera energiuttaget från alla de elmätare som finns under nätstationerna som hämtas från insamlingssystemet CustCom. Här får man timrapporten för varje kunds energiförbrukning. Man är då särdeles intresserad av den dagen då nätet var som hårdast belastat. Detta skedde under julhelgen 22 december 2010 klockan 16.00. Den andra metoden är att få fram värden genom beräkningar via javaprogrammet Facilplus. Programmet används även för nätdokumentation (var stationerna och kablar befinner sig geografiskt) och projektering av utbyggnaderna. Belastningsberäkningarna i Facilplus använder sig av Velanders formel för att räkna fram effekten från kända årsförbrukningar av Karlstad Elnät AB:s kunder. När det gäller att prognosera effektanvändningen för nybebyggelserna, beräknas först ett standardvärde för respektive byggnad (specifik energiförbrukning). Detta värde beräknas med hjälp av byggnaders ytor utifrån begärda ritningar från några noga utvalda områden. Därefter kan energianvändningen per kvadratmeter beräknas utifrån uppmätt energiförbrukning för de kunderna i respektive byggnad. Omvandlingen sker sedan från energiförbrukning till effektförbrukning och man får därmed ett bra mått på hur en viss byggnadstyp har för energianvändning. Då antalet bostäder som ska byggas ut under perioden är kända från de byggnadsplaner som är tillgängliga för allmänheten kan man sedermera få fram en översiktlig storlek för varje nybyggnadsområdes framtida energianvändning. Det kommer även sålunda bli möjligt att avgöra om elnätet bör byggas ut eller om stationer ska omplaceras så att de hamnar inom andra mottagningsstationers matningsområden. Befintliga mottagningsstationer har kapacitet för ytterligare utbyggnad av Karlstad i olika riktningar.
Morabit, Safaa El. « New Artificial Intelligence techniques for Computer vision based medical diagnosis ». Electronic Thesis or Diss., Valenciennes, Université Polytechnique Hauts-de-France, 2023. http://www.theses.fr/2023UPHF0013.
Texte intégralThe ability to feel pain is crucial for life, since it serves as an early warning system forpotential harm to the body. The majority of pain evaluations rely on patient reports. Patients who are unable to express their own pain must instead rely on third-party reportsof their suffering. Due to potential observer bias, pain reports may contain inaccuracies. In addition, it would be impossible for people to keep watch around the clock. Inorder to better manage pain, especially in noncommunicative patients, automatic paindetection technologies might be implemented to aid human caregivers and complementtheir service. Facial expressions are used by all observer-based pain assessment systemsbecause they are a reliable indicator of pain and can be interpreted from a distance.Taking into consideration that pain generally generates spontaneous facial behavior,these facial expressions could be used to detect the presence of pain. In this thesis, weanalyze facial expressions of pain in order to address pain estimation. First, we presenta thorough analysis of the problem by comparing numerous common CNN (Convolutional Neural Network) architectures, such as MobileNet, GoogleNet, ResNeXt-50, ResNet18, and DenseNet-161. We employ these networks in two unique modes: standalone and feature extraction. In standalone mode, models (i.e., networks) are utilized to directly estimate pain. In feature extractor mode, "values" from the middle layer are extracted and fed into classifiers like Support Vector Regression (SVR) and Random Forest Regression (RFR).CNNs have achieved significant results in image classification and have achievedgreat success. The effectiveness of Transformers in computer vision has been demonstrated through recent studies. Transformer-based architectures were proposed in the second section of this thesis. Two distinct Transformer-based frameworks were presented to address two distinct pain issues: pain detection (pain vs no pain) and thedistinction between genuine and posed pain. The innovative architecture for binaryidentification of facial pain is based on data-efficient image transformers (Deit). Twodatasets, UNBC-McMaster shoulder pain and BioVid heat pain, were used to fine-tuneand assess the trained model. The suggested architecture is built on Vision Transformers for the detection of genuine and simulated pain from facial expressions (ViT). Todistinguish between Genuine and Posed Pain, the model must pay particular attentionto the subtle changes in facial expressions over time. The employed approach takes intoaccount the sequential aspect and captures the variations in facial expressions. Experiments on the publicly accessible BioVid Heat Pain Database demonstrate the efficacy of our strategy
Ganin, Iaroslav. « Natural image processing and synthesis using deep learning ». Thèse, 2019. http://hdl.handle.net/1866/23437.
Texte intégralIn the present thesis, we study how deep neural networks can be applied to various tasks in computer vision. Computer vision is an interdisciplinary field that deals with understanding of digital images and video. Traditionally, the problems arising in this domain were tackled using heavily hand-engineered adhoc methods. A typical computer vision system up until recently consisted of a sequence of independent modules which barely talked to each other. Such an approach is quite reasonable in the case of limited data as it takes major advantage of the researcher's domain expertise. This strength turns into a weakness if some of the input scenarios are overlooked in the algorithm design process. With the rapidly increasing volumes and varieties of data and the advent of cheaper and faster computational resources end-to-end deep neural networks have become an appealing alternative to the traditional computer vision pipelines. We demonstrate this in a series of research articles, each of which considers a particular task of either image analysis or synthesis and presenting a solution based on a ``deep'' backbone. In the first article, we deal with a classic low-level vision problem of edge detection. Inspired by a top-performing non-neural approach, we take a step towards building an end-to-end system by combining feature extraction and description in a single convolutional network. The resulting fully data-driven method matches or surpasses the detection quality of the existing conventional approaches in the settings for which they were designed while being significantly more usable in the out-of-domain situations. In our second article, we introduce a custom architecture for image manipulation based on the idea that most of the pixels in the output image can be directly copied from the input. This technique bears several significant advantages over the naive black-box neural approach. It retains the level of detail of the original images, does not introduce artifacts due to insufficient capacity of the underlying neural network and simplifies training process, to name a few. We demonstrate the efficiency of the proposed architecture on the challenging gaze correction task where our system achieves excellent results. In the third article, we slightly diverge from pure computer vision and study a more general problem of domain adaption. There, we introduce a novel training-time algorithm (\ie, adaptation is attained by using an auxilliary objective in addition to the main one). We seek to extract features that maximally confuse a dedicated network called domain classifier while being useful for the task at hand. The domain classifier is learned simultaneosly with the features and attempts to tell whether those features are coming from the source or the target domain. The proposed technique is easy to implement, yet results in superior performance in all the standard benchmarks. Finally, the fourth article presents a new kind of generative model for image data. Unlike conventional neural network based approaches our system dubbed SPIRAL describes images in terms of concise low-level programs executed by off-the-shelf rendering software used by humans to create visual content. Among other things, this allows SPIRAL not to waste its capacity on minutae of datasets and focus more on the global structure. The latent space of our model is easily interpretable by design and provides means for predictable image manipulation. We test our approach on several popular datasets and demonstrate its power and flexibility.