Teses / dissertações sobre o tema "Apprentissage de la représentation visuelle"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 50 melhores trabalhos (teses / dissertações) para estudos sobre o assunto "Apprentissage de la représentation visuelle".
Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.
Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.
Veja as teses / dissertações das mais diversas áreas científicas e compile uma bibliografia correta.
Risser-Maroix, Olivier. "Similarité visuelle et apprentissage de représentations". Electronic Thesis or Diss., Université Paris Cité, 2022. http://www.theses.fr/2022UNIP7327.
Texto completo da fonteThe objective of this CIFRE thesis is to develop an image search engine, based on computer vision, to assist customs officers. Indeed, we observe, paradoxically, an increase in security threats (terrorism, trafficking, etc.) coupled with a decrease in the number of customs officers. The images of cargoes acquired by X-ray scanners already allow the inspection of a load without requiring the opening and complete search of a controlled load. By automatically proposing similar images, such a search engine would help the customs officer in his decision making when faced with infrequent or suspicious visual signatures of products. Thanks to the development of modern artificial intelligence (AI) techniques, our era is undergoing great changes: AI is transforming all sectors of the economy. Some see this advent of "robotization" as the dehumanization of the workforce, or even its replacement. However, reducing the use of AI to the simple search for productivity gains would be reductive. In reality, AI could allow to increase the work capacity of humans and not to compete with them in order to replace them. It is in this context, the birth of Augmented Intelligence, that this thesis takes place. This manuscript devoted to the question of visual similarity is divided into two parts. Two practical cases where the collaboration between Man and AI is beneficial are proposed. In the first part, the problem of learning representations for the retrieval of similar images is still under investigation. After implementing a first system similar to those proposed by the state of the art, one of the main limitations is pointed out: the semantic bias. Indeed, the main contemporary methods use image datasets coupled with semantic labels only. The literature considers that two images are similar if they share the same label. This vision of the notion of similarity, however fundamental in AI, is reductive. It will therefore be questioned in the light of work in cognitive psychology in order to propose an improvement: the taking into account of visual similarity. This new definition allows a better synergy between the customs officer and the machine. This work is the subject of scientific publications and a patent. In the second part, after having identified the key components allowing to improve the performances of thepreviously proposed system, an approach mixing empirical and theoretical research is proposed. This secondcase, augmented intelligence, is inspired by recent developments in mathematics and physics. First applied tothe understanding of an important hyperparameter (temperature), then to a larger task (classification), theproposed method provides an intuition on the importance and role of factors correlated to the studied variable(e.g. hyperparameter, score, etc.). The processing chain thus set up has demonstrated its efficiency byproviding a highly explainable solution in line with decades of research in machine learning. These findings willallow the improvement of previously developed solutions
Saxena, Shreyas. "Apprentissage de représentations pour la reconnaissance visuelle". Thesis, Université Grenoble Alpes (ComUE), 2016. http://www.theses.fr/2016GREAM080/document.
Texto completo da fonteIn this dissertation, we propose methods and data driven machine learning solutions which address and benefit from the recent overwhelming growth of digital media content.First, we consider the problem of improving the efficiency of image retrieval. We propose a coordinated local metric learning (CLML) approach which learns local Mahalanobis metrics, and integrates them in a global representation where the l2 distance can be used. This allows for data visualization in a single view, and use of efficient ` 2 -based retrieval methods. Our approach can be interpreted as learning a linear projection on top of an explicit high-dimensional embedding of a kernel. This interpretation allows for the use of existing frameworks for Mahalanobis metric learning for learning local metrics in a coordinated manner. Our experiments show that CLML improves over previous global and local metric learning approaches for the task of face retrieval.Second, we present an approach to leverage the success of CNN models forvisible spectrum face recognition to improve heterogeneous face recognition, e.g., recognition of near-infrared images from visible spectrum training images. We explore different metric learning strategies over features from the intermediate layers of the networks, to reduce the discrepancies between the different modalities. In our experiments we found that the depth of the optimal features for a given modality, is positively correlated with the domain shift between the source domain (CNN training data) and the target domain. Experimental results show the that we can use CNNs trained on visible spectrum images to obtain results that improve over the state-of-the art for heterogeneous face recognition with near-infrared images and sketches.Third, we present convolutional neural fabrics for exploring the discrete andexponentially large CNN architecture space in an efficient and systematic manner. Instead of aiming to select a single optimal architecture, we propose a “fabric” that embeds an exponentially large number of architectures. The fabric consists of a 3D trellis that connects response maps at different layers, scales, and channels with a sparse homogeneous local connectivity pattern. The only hyperparameters of the fabric (the number of channels and layers) are not critical for performance. The acyclic nature of the fabric allows us to use backpropagation for learning. Learning can thus efficiently configure the fabric to implement each one of exponentially many architectures and, more generally, ensembles of all of them. While scaling linearly in terms of computation and memory requirements, the fabric leverages exponentially many chain-structured architectures in parallel by massively sharing weights between them. We present benchmark results competitive with the state of the art for image classification on MNIST and CIFAR10, and for semantic segmentation on the Part Labels dataset
Tamaazousti, Youssef. "Vers l’universalité des représentations visuelle et multimodales". Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLC038/document.
Texto completo da fonteBecause of its key societal, economic and cultural stakes, Artificial Intelligence (AI) is a hot topic. One of its main goal, is to develop systems that facilitates the daily life of humans, with applications such as household robots, industrial robots, autonomous vehicle and much more. The rise of AI is highly due to the emergence of tools based on deep neural-networks which make it possible to simultaneously learn, the representation of the data (which were traditionally hand-crafted), and the task to solve (traditionally learned with statistical models). This resulted from the conjunction of theoretical advances, the growing computational capacity as well as the availability of many annotated data. A long standing goal of AI is to design machines inspired humans, capable of perceiving the world, interacting with humans, in an evolutionary way. We categorize, in this Thesis, the works around AI, in the two following learning-approaches: (i) Specialization: learn representations from few specific tasks with the goal to be able to carry out very specific tasks (specialized in a certain field) with a very good level of performance; (ii) Universality: learn representations from several general tasks with the goal to perform as many tasks as possible in different contexts. While specialization was extensively explored by the deep-learning community, only a few implicit attempts were made towards universality. Thus, the goal of this Thesis is to explicitly address the problem of improving universality with deep-learning methods, for image and text data. We have addressed this topic of universality in two different forms: through the implementation of methods to improve universality (“universalizing methods”); and through the establishment of a protocol to quantify its universality. Concerning universalizing methods, we proposed three technical contributions: (i) in a context of large semantic representations, we proposed a method to reduce redundancy between the detectors through, an adaptive thresholding and the relations between concepts; (ii) in the context of neural-network representations, we proposed an approach that increases the number of detectors without increasing the amount of annotated data; (iii) in a context of multimodal representations, we proposed a method to preserve the semantics of unimodal representations in multimodal ones. Regarding the quantification of universality, we proposed to evaluate universalizing methods in a Transferlearning scheme. Indeed, this technical scheme is relevant to assess the universal ability of representations. This also led us to propose a new framework as well as new quantitative evaluation criteria for universalizing methods
Lienou, Marie Lauginie. "Apprentissage automatique des classes d'occupation du sol et représentation en mots visuels des images satellitaires". Phd thesis, Paris, ENST, 2009. https://pastel.hal.science/pastel-00005585.
Texto completo da fonteLand cover recognition from automatic classifications is one of the important methodological researches in remote sensing. Besides, getting results corresponding to the user expectations requires approaching the classification from a semantic point of view. Within this frame, this work aims at the elaboration of automatic methods capable of learning classes defined by cartography experts, and of automatically annotating unknown images based on this classification. Using corine land cover maps, we first show that classical approaches in the state-of-the-art are able to well-identify homogeneous classes such as fields, but have difficulty in finding high-level semantic classes, also called mixed classes because they consist of various land cover categories. To detect such classes, we represent images into visual words, in order to use text analysis tools which showed their efficiency in the field of text mining. By means of supervised and not supervised approaches on one hand, we exploit the notion of semantic compositionality: image structures which are considered as mixtures of land cover types, are detected by bringing out the importance of spatial relations between the visual words. On the other hand, we propose a semantic annotation method using a statistical text analysis model: latent dirichlet allocation. We rely on this mixture model, which requires a bags-of-words representation of images, to properly model high-level semantic classes. The proposed approach and the comparative studies with gaussian and gmm models, as well as svm classifier, are assessed using spot and quickbird images among others
Lienou, Marie Lauginie. "Apprentissage automatique des classes d'occupation du sol et représentation en mots visuels des images satellitaires". Phd thesis, Télécom ParisTech, 2009. http://pastel.archives-ouvertes.fr/pastel-00005585.
Texto completo da fonteEl-Zakhem, Imad. "Modélisation et apprentissage des perceptions humaines à travers des représentations floues : le cas de la couleur". Reims, 2009. http://theses.univ-reims.fr/exl-doc/GED00001090.pdf.
Texto completo da fonteThe target of this thesis is to implement an interactive modeling of the user perception and a creation of an appropriate profile. We present two methods to build the profile representing the perception of the user through fuzzy subsets. The first method is a descriptive method used by an expert user and the second one is a constructive method used by a none-expert user. For the descriptive method, we propose a questioning procedure allowing the user to define completely his profile. For the constructive method, the user will be able to define his perception while comparing and selecting some profiles reflecting the perception of other expert users. We present a procedure of aggregation allowing building the profile of the user starting from the selected expert profiles and the rates of satisfaction. As a case study, we describe an application to model the color perception. Thereafter, we exploit the profiles already built for image classification. We propose a procedure that allows building the profile of an image according to the user perception, by using the standard profile of the image and the user’s profile representing his perception. In this method we use new definitions for the notions of comparability and compatibility of two fuzzy subsets. At the end, we present an implementation of the all procedure, the structure of the database as some examples and results
Engilberge, Martin. "Deep Inside Visual-Semantic Embeddings". Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS150.
Texto completo da fonteNowadays Artificial Intelligence (AI) is omnipresent in our society. The recentdevelopment of learning methods based on deep neural networks alsocalled "Deep Learning" has led to a significant improvement in visual representation models.and textual.In this thesis, we aim to further advance image representation and understanding.Revolving around Visual Semantic Embedding (VSE) approaches, we explore different directions: We present relevant background covering images and textual representation and existing multimodal approaches. We propose novel architectures further improving retrieval capability of VSE and we extend VSE models to novel applications and leverage embedding models to visually ground semantic concept. Finally, we delve into the learning process andin particular the loss function by learning differentiable approximation of ranking based metric
Venkataramanan, Shashanka. "Metric learning for instance and category-level visual representation". Electronic Thesis or Diss., Université de Rennes (2023-....), 2024. http://www.theses.fr/2024URENS022.
Texto completo da fonteThe primary goal in computer vision is to enable machines to extract meaningful information from visual data, such as images and videos, and leverage this information to perform a wide range of tasks. To this end, substantial research has focused on developing deep learning models capable of encoding comprehensive and robust visual representations. A prominent strategy in this context involves pretraining models on large-scale datasets, such as ImageNet, to learn representations that can exhibit cross-task applicability and facilitate the successful handling of diverse downstream tasks with minimal effort. To facilitate learning on these large-scale datasets and encode good representations, com- plex data augmentation strategies have been used. However, these augmentations can be limited in their scope, either being hand-crafted and lacking diversity, or generating images that appear unnatural. Moreover, the focus of these augmentation techniques has primarily been on the ImageNet dataset and its downstream tasks, limiting their applicability to a broader range of computer vision problems. In this thesis, we aim to tackle these limitations by exploring different approaches to en- hance the efficiency and effectiveness in representation learning. The common thread across the works presented is the use of interpolation-based techniques, such as mixup, to generate diverse and informative training examples beyond the original dataset. In the first work, we are motivated by the idea of deformation as a natural way of interpolating images rather than using a convex combination. We show that geometrically aligning the two images in the fea- ture space, allows for more natural interpolation that retains the geometry of one image and the texture of the other, connecting it to style transfer. Drawing from these observations, we explore the combination of mixup and deep metric learning. We develop a generalized formu- lation that accommodates mixup in metric learning, leading to improved representations that explore areas of the embedding space beyond the training classes. Building on these insights, we revisit the original motivation of mixup and generate a larger number of interpolated examples beyond the mini-batch size by interpolating in the embedding space. This approach allows us to sample on the entire convex hull of the mini-batch, rather than just along lin- ear segments between pairs of examples. Finally, we investigate the potential of using natural augmentations of objects from videos. We introduce a "Walking Tours" dataset of first-person egocentric videos, which capture a diverse range of objects and actions in natural scene transi- tions. We then propose a novel self-supervised pretraining method called DoRA, which detects and tracks objects in video frames, deriving multiple views from the tracks and using them in a self-supervised manner
Nguyen, Nhu Van. "Représentations visuelles de concepts textuels pour la recherche et l'annotation interactives d'images". Phd thesis, Université de La Rochelle, 2011. http://tel.archives-ouvertes.fr/tel-00730707.
Texto completo da fonteDefrasne, Ait-Said Elise. "Perception et représentation du mouvement : influences de la verbalisation sur la reconnaissance de mouvements d'escrime en fonction de l'expertise". Thesis, Besançon, 2014. http://www.theses.fr/2014BESA1023/document.
Texto completo da fonteIs it necessary to verbalize in order to memorize and learn a material? According to the literature examining the influence of verbalizations on learning and memory, the answer to this question depends on the type of material used (conceptual material versus perceptive material) and on the learners’ level of expertise. In Study 1, we examined the influence of verbal descriptions on the visual recognition of sequences of fencing movements, with participants of the three levels of expertise (novices, intermediates, experts). In Study 2, we studied the influence of different content of verbal descriptions on the recognition of sequences of fencing movements, according to the level of expertise. The goal of Study 3 was to examine the effect on memory of a trace distinct from a verbal trace: a motor trace. The findings of Study 1 show that verbalizing improves novices’ recognition, impairs intermediates’ recognition and has no effect on experts’ recognition. The results of Study 2 show that the content of verbal descriptions has an effect on memory, according to the participants’ level of expertise. The findings of Study 3 show that duplicating the fencing movement, with no feedback, strongly impedes beginners’ visual recognition. These findings broaden the verbal overshadowing phenomena to a material distinctly more conceptual than the one classically used in this field of research. They bring strong support to the theoretical hypothesis of interference resulting from a verbal recoding (Schooler, 1990). They also show that an additional motor trace can harm visual recognition of movement sequences
Mazari, Ahmed. "Apprentissage profond pour la reconnaissance d’actions en vidéos". Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS171.
Texto completo da fonteNowadays, video contents are ubiquitous through the popular use of internet and smartphones, as well as social media. Many daily life applications such as video surveillance and video captioning, as well as scene understanding require sophisticated technologies to process video data. It becomes of crucial importance to develop automatic means to analyze and to interpret the large amount of available video data. In this thesis, we are interested in video action recognition, i.e. the problem of assigning action categories to sequences of videos. This can be seen as a key ingredient to build the next generation of vision systems. It is tackled with AI frameworks, mainly with ML and Deep ConvNets. Current ConvNets are increasingly deeper, data-hungrier and this makes their success tributary of the abundance of labeled training data. ConvNets also rely on (max or average) pooling which reduces dimensionality of output layers (and hence attenuates their sensitivity to the availability of labeled data); however, this process may dilute the information of upstream convolutional layers and thereby affect the discrimination power of the trained video representations, especially when the learned action categories are fine-grained
Caissié, André. "Étude des transferts intermodaux lors de taches de rotation mentale : spécificité tactile, indépendance sensorielle ou dépendance visuelle ?" Thesis, Poitiers, 2012. http://www.theses.fr/2012POIT5002/document.
Texto completo da fonteThe work presented in this dissertation is based on the combination of two research paradigms in the field of cognitive psychology: mental rotation and intermodal/inter-task transfer of learning. In our first study (Experiments 1a, 1b, 1c, 2a, and 2b), the objective was to evaluate the processing dependence/independence of visual and tactile information during two mental rotation tasks: the Mental Rotation Test (Vandenberg & Kuse, 1978) and an object mental rotation task (Shepard & Metzler, 1971). Using an intra-subject experimental design, we compared four experimental conditions including intramodal learning: 1. Visual-Visual ; 2. Tactile-Tactile, and intermodal transfer: 3. Visual-Tactile ; 4. Tactile-Visual. Subjects performed two successive tasks in similar perceptual conditions or different perceptual conditions (session 1 and session 2). Our results revealed that mental rotation can depend on treatment processes of mental representations specific to the perceptual modality being used. The information derived from visual prior experience can be used in the tactile condition, whereas we observed few significant tactile transfers in the visual condition. Visual and tactile treatments on complex three-dimensional objects thus permit specific mental imagery strategies (Visual-Visual-IM vs. Tactile-Spatial-IM), derived from different perceptual exploration strategies (visual-global vs. tactile-spatial)
Goh, Hanlin. "Apprentissage de Représentations Visuelles Profondes". Phd thesis, Université Pierre et Marie Curie - Paris VI, 2013. http://tel.archives-ouvertes.fr/tel-00948376.
Texto completo da fonteLerner, Paul. "Répondre aux questions visuelles à propos d'entités nommées". Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPASG074.
Texto completo da fonteThis thesis is positioned at the intersection of several research fields, Natural Language Processing, Information Retrieval (IR) and Computer Vision, which have unified around representation learning and pre-training methods. In this context, we have defined and studied a new multimodal task: Knowledge-based Visual Question Answering about Named Entities (KVQAE).In this context, we were particularly interested in cross-modal interactions and different ways of representing named entities. We also focused on data used to train and, more importantly, evaluate Question Answering systems through different metrics.More specifically, we proposed a dataset for this purpose, the first in KVQAE comprising various types of entities. We also defined an experimental framework for dealing with KVQAE in two stages through an unstructured knowledge base and identified IR as the main bottleneck of KVQAE, especially for questions about non-person entities. To improve the IR stage, we studied different multimodal fusion methods, which are pre-trained through an original task: the Multimodal Inverse Cloze Task. We found that these models leveraged a cross-modal interaction that we had not originally considered, and which may address the heterogeneity of visual representations of named entities. These results were strengthened by a study of the CLIP model, which allows this cross-modal interaction to be modeled directly. These experiments were carried out while staying aware of biases present in the dataset or evaluation metrics, especially of textual biases, which affect any multimodal task
Senoussi, Medhi. "Flexibilité temporelle et spatiale des représentations neurales d'objets visuels lors d'apprentissages". Thesis, Toulouse 3, 2016. http://www.theses.fr/2016TOU30162.
Texto completo da fonteThe work presented in this thesis deals with the effect of short- and long-term learning on the visual system. We first demonstrated through electroencephalographic recordings that learning a sequence of visual stimuli induced spontaneous and selective cerebral activity to the next-to-appear stimulus and that this selective activity was expressed in the alpha and beta bands of cerebral electrical activity. Subsequently, we showed through functional magnetic resonance imaging that during long learning (three weeks) the neural representations of associated visual categories were modulated and became more similar due to learning. The work presented in this thesis has thus made it possible to better characterize the impact of learning at different time scales on the neural representations of visual objects
Bigot, Damien. "Représentation et apprentissage de préférences". Thesis, Toulouse 3, 2015. http://www.theses.fr/2015TOU30031/document.
Texto completo da fonte--
Mordan, Taylor. "Conception d'architectures profondes pour l'interprétation de données visuelles". Electronic Thesis or Diss., Sorbonne université, 2018. http://www.theses.fr/2018SORUS270.
Texto completo da fonteNowadays, images are ubiquitous through the use of smartphones and social media. It then becomes necessary to have automatic means of processing them, in order to analyze and interpret the large amount of available data. In this thesis, we are interested in object detection, i.e. the problem of identifying and localizing all objects present in an image. This can be seen as a first step toward a complete visual understanding of scenes. It is tackled with deep convolutional neural networks, under the Deep Learning paradigm. One drawback of this approach is the need for labeled data to learn from. Since precise annotations are time-consuming to produce, bigger datasets can be built with partial labels. We design global pooling functions to work with them and to recover latent information in two cases: learning spatially localized and part-based representations from image- and object-level supervisions respectively. We address the issue of efficiency in end-to-end learning of these representations by leveraging fully convolutional networks. Besides, exploiting additional annotations on available images can be an alternative to having more images, especially in the data-deficient regime. We formalize this problem as a specific kind of multi-task learning with a primary objective to focus on, and design a way to effectively learn from this auxiliary supervision under this framework
Paulin, Mattis. "De l'apprentissage de représentations visuelles robustes aux invariances pour la classification et la recherche d'images". Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAM007/document.
Texto completo da fonteThis dissertation focuses on designing image recognition systems which are robust to geometric variability. Image understanding is a difficult problem, as images are two-dimensional projections of 3D objects, and representations that must fall into the same category, for instance objects of the same class in classification can display significant differences. Our goal is to make systems robust to the right amount of deformations, this amount being automatically determined from data. Our contributions are twofolds. We show how to use virtual examples to enforce robustness in image classification systems and we propose a framework to learn robust low-level descriptors for image retrieval. We first focus on virtual examples, as transformation of real ones. One image generates a set of descriptors –one for each transformation– and we show that data augmentation, ie considering them all as iid samples, is the best performing method to use them, provided a voting stage with the transformed descriptors is conducted at test time. Because transformations have various levels of information, can be redundant, and can even be harmful to performance, we propose a new algorithm able to select a set of transformations, while maximizing classification accuracy. We show that a small amount of transformations is enough to considerably improve performance for this task. We also show how virtual examples can replace real ones for a reduced annotation cost. We report good performance on standard fine-grained classification datasets. In a second part, we aim at improving the local region descriptors used in image retrieval and in particular to propose an alternative to the popular SIFT descriptor. We propose new convolutional descriptors, called patch-CKN, which are learned without supervision. We introduce a linked patch- and image-retrieval dataset based on structure from motion of web-crawled images, and design a method to accurately test the performance of local descriptors at patch and image levels. Our approach outperforms both SIFT and all tested approaches with convolutional architectures on our patch and image benchmarks, as well as several styate-of-theart datasets
Tomasini, Linda. "Apprentissage d'une représentation statistique et topologique d'un environnement". Toulouse, ENSAE, 1993. http://www.theses.fr/1993ESAE0024.
Texto completo da fonteChabiron, Olivier. "Apprentissage d'arbres de convolutions pour la représentation parcimonieuse". Thesis, Toulouse 3, 2015. http://www.theses.fr/2015TOU30213/document.
Texto completo da fonteThe dictionary learning problem has received increasing attention for the last ten years. DL is an adaptive approach for sparse data representation. Many state-of-the-art DL methods provide good performances for problems such as approximation, denoising and inverse problems. However, their numerical complexity restricts their use to small image patches. Thus, dictionary learning does not capture large features and is not a viable option for many applications handling large images, such as those encountered in remote sensing. In this thesis, we propose and study a new model for dictionary learning, combining convolutional sparse coding and dictionaries defined by convolutional tree structures. The aim of this model is to provide efficient algorithms for large images, avoiding the decomposition of these images into patches. In the first part, we study the optimization of a composition of convolutions with sparse kernels, to reach a target atom (such as a cosine, wavelet or curvelet). This is a non-convex matrix factorization problem. We propose a resolution method based on a Gaus-Seidel scheme, which produces good approximations of target atoms and whose complexity is linear with respect to the image size. Moreover, numerical experiments show that it is possible to find a global minimum. In the second part, we introduce a dictionary structure based on convolutional trees. We propose a dictionary update algorithm adapted to this structure and which complexity remains linear with respect to the image size. Finally, a sparse coding step is added to the algorithm in the last part. For each evolution of the proposed method, we illustrate its approximation abilities with numerical experiments
El, Sayad Ismail. "Une représentation visuelle avancée pour l'apprentissage sémantique dans les bases d'images". Phd thesis, Université des Sciences et Technologie de Lille - Lille I, 2011. http://tel.archives-ouvertes.fr/tel-00666531.
Texto completo da fonteLauret, Gérard. "Représentation en architecture et image informatique". Paris 8, 1995. http://www.theses.fr/1995PA081081.
Texto completo da fonteArchitecture is a big consumer of pictures and representation. Do the new technologies, and in particular synthesis pictures bring a new method of representation, or do they inscribe themselves in the following of old manners ? an approach historical, technical and philosophical, who is setting the specificity of architecture and new technological instrument, and define the place of synthesis pictures in the representation of building in architecture
Lekdioui, Khadija. "Reconnaissance d'états émotionnels par analyse visuelle du visage et apprentissage machine". Thesis, Bourgogne Franche-Comté, 2018. http://www.theses.fr/2018UBFCA042/document.
Texto completo da fonteIn face-to-face settings, an act of communication includes verbal and emotional expressions. From observation, diagnosis and identification of the individual's emotional state, the interlocutor will undertake actions that would influence the quality of the communication. In this regard, we suggest to improve the way that the individuals perceive their exchanges by proposing to enrich the textual computer-mediated communication by emotions felt by the collaborators. To do this, we propose to integrate a real time emotions recognition system in a platform “Moodle”, to extract them from the analysis of facial expressions of the distant learner in collaborative activities. There are three steps to recognize facial expressions. First, the face and its components (eyebrows, nose, mouth, eyes) are detected from the configuration of facial landmarks. Second, a combination of heterogeneous descriptors is used to extract the facial features. Finally, a classifier is applied to classify these features into six predefined emotions as well as the neutral state. The performance of the proposed system will be assessed on a public basis of posed and spontaneous facial expressions such as Cohn-Kanade (CK), Karolinska Directed Emotional Faces (KDEF) and Facial Expressions and Emotion Database (FEED)
Deschamps, Sébastien. "Apprentissage actif profond pour la reconnaissance visuelle à partir de peu d’exemples". Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS199.
Texto completo da fonteAutomatic image analysis has improved the exploitation of image sensors, with data coming from different sensors such as phone cameras, surveillance cameras, satellite imagers or even drones. Deep learning achieves excellent results in image analysis applications where large amounts of annotated data are available, but learning a new image classifier from scratch is a difficult task. Most image classification methods are supervised, requiring annotations, which is a significant investment. Different frugal learning solutions (with few annotated examples) exist, including transfer learning, active learning, semi-supervised learning or meta-learning. The goal of this thesis is to study these frugal learning solutions for visual recognition tasks, namely image classification and change detection in satellite images. The classifier is trained iteratively by starting with only a few annotated samples, and asking the user to annotate as little data as possible to obtain satisfactory performance. Deep active learning was initially studied with other methods and suited our operational problem the most, so we chose this solution. In this thesis, we have developed an interactive approach, where we ask the most informative questions about the relevance of the data to an oracle (annotator). Based on its answers, a decision function is iteratively updated. We model the probability that the samples are relevant, by minimizing an objective function capturing the representativeness, diversity and ambiguity of the data. Data with high probability are then selected for annotation. We have improved this approach, using reinforcement learning to dynamically and accurately weight the importance of representativeness, diversity and ambiguity of the data in each active learning cycle. Finally, our last approach consists of a display model that selects the most representative and diverse virtual examples, which adversely challenge the learned model, in order to obtain a highly discriminative model in subsequent iterations of active learning. The good results obtained against the different baselines and the state of the art in the tasks of satellite image change detection and image classification have demonstrated the relevance of the proposed frugal learning models, and have led to various publications (Sahbi et al. 2021; Deschamps and Sahbi 2022b; Deschamps and Sahbi 2022a; Sahbi and Deschamps2022)
Poussevin, Mickael. "Apprentissage de représentation pour des données générées par des utilisateurs". Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066040/document.
Texto completo da fonteIn this thesis, we study how representation learning methods can be applied to user-generated data. Our contributions cover three different applications but share a common denominator: the extraction of relevant user representations. Our first application is the item recommendation task, where recommender systems build user and item profiles out of past ratings reflecting user preferences and item characteristics. Nowadays, textual information is often together with ratings available and we propose to use it to enrich the profiles extracted from the ratings. Our hope is to extract from the textual content shared opinions and preferences. The models we propose provide another opportunity: predicting the text a user would write on an item. Our second application is sentiment analysis and, in particular, polarity classification. Our idea is that recommender systems can be used for such a task. Recommender systems and traditional polarity classifiers operate on different time scales. We propose two hybridizations of these models: the former has better classification performance, the latter highlights a vocabulary of surprise in the texts of the reviews. The third and final application we consider is urban mobility. It takes place beyond the frontiers of the Internet, in the physical world. Using authentication logs of the subway users, logging the time and station at which users take the subway, we show that it is possible to extract robust temporal profiles
Poussevin, Mickael. "Apprentissage de représentation pour des données générées par des utilisateurs". Electronic Thesis or Diss., Paris 6, 2015. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2015PA066040.pdf.
Texto completo da fonteIn this thesis, we study how representation learning methods can be applied to user-generated data. Our contributions cover three different applications but share a common denominator: the extraction of relevant user representations. Our first application is the item recommendation task, where recommender systems build user and item profiles out of past ratings reflecting user preferences and item characteristics. Nowadays, textual information is often together with ratings available and we propose to use it to enrich the profiles extracted from the ratings. Our hope is to extract from the textual content shared opinions and preferences. The models we propose provide another opportunity: predicting the text a user would write on an item. Our second application is sentiment analysis and, in particular, polarity classification. Our idea is that recommender systems can be used for such a task. Recommender systems and traditional polarity classifiers operate on different time scales. We propose two hybridizations of these models: the former has better classification performance, the latter highlights a vocabulary of surprise in the texts of the reviews. The third and final application we consider is urban mobility. It takes place beyond the frontiers of the Internet, in the physical world. Using authentication logs of the subway users, logging the time and station at which users take the subway, we show that it is possible to extract robust temporal profiles
LERCH, CHRISTOPHE. "Une nouvelle représentation du contrôle organisationnel : le pilotage des processus". Université Louis Pasteur (Strasbourg) (1971-2008), 1998. http://www.theses.fr/1998STR1EC01.
Texto completo da fonteThe crisis of management instrumentation wich appeared in the 80's can be interpreted as a crisis of the representation modes of organization. Therfore this thesis offers some thoughts on the type of organization aimed at controlling, starting from a model based an activities. First, we use graphical representations in order to model the activities of organisations in applied cases. Our analysis identifies some limits the functional tools which are most frequently used. We then suggest some solutions by resorting to a cognitive representation of the activities. Secondly, we develop a typology which structures the diversity of the processes. We distinguish three categories : the structured process, the semi-structured process, the non structured process. Those configurations can in particular be differentiated by their strategies of environmental adaptation and their structure of management. The objective to provide a language so as to facilitate the diagnosis on the functioning of the processes. Our study resulted in devising a dashboard intended to drive the collective mechanisms of adaptation and knowledge creation. Our analysis emphasises both the parameters of control of these mechanisms and the impact of those parameters on the dynamic of the learning processes. Finally, managing the processes appears to be a way to mobilise the cognitive attention of the actors of the organisation. The point is especially important when the operators have to solve radically new problems of strategic importance for the organisation and thus need to explore new. Fields of knowledge. Conversely, managing the processes helps to save the cognitive resources of the organisation in situations where the members have to solve well-defined and well-known problems by exploiting available and explicit knowledge
Liucci, Nicolas. "Le spectateur en place : représentation des classes sociales dans l'imagerie contemporaine". Paris, EHESS, 2010. http://www.theses.fr/2010EHES0150.
Texto completo da fonteIssues. During the last three decades, the existence of social classes has been questioned. The recent social evolution has led to the rehabilitation of the "class-conscious" sociological standpoint. Advertising. Some goods, such as clothes and cars, allow their owner to express a certain social status. The interpretation demonstrates marked differences between down-market and up-market advertisements. The iconic analysis shows that the characters are represented in various ways, recalling the topical descriptions of the class structure. This makes clear that a hierarchy of styles exists very similar to the ancient Rhetoric hierarchy. Not only advertising carries a quintessentially conservative representation of the c1ass structure, addressing each one in a hierarchical style, in order to put the viewer in his due place. It is also supporting an ideological vision of the social structure, where the Iower class is merely depicted as debased version of the upper class, as a class deprived of means, a class defined according to what it does not have. Art. The more you climb up to the up-market, in advertising, the more you notice the use of "artistic" languages -including the absence of stereotypes and the manipulation of specific lexicons. Compared to advertising, Art produces "disturbing" pictures -pictures, which would try to challenge the symbolic distribution of places. The analysis shows that specific artworks overthrow the previously established hierarchies, and endeavor to loose the viewer in collages of incongruous elements, in order to arouse his reflection. But it also appears that the "exclusive" context in which the artwork exists alters its subversive potential
Chessel, Anatole. "Vision par ordinateur et otolithe : de la perception visuelle à une représentation des connaissances". Rennes 1, 2007. http://www.theses.fr/2007REN1S184.
Texto completo da fonteThis work studies the application of computer vision methods to the analysis of fish otoliths. Fish otoliths are small calcerous concretions set in fishes inner ears of much interest in biology and ecology. From both biological and perceptual analysis, two informations from otoliths sections images are characterised as being useful and important in the analysis and use of otolith: the global geometrical evolution of the outline, and the growth rings, corresponding to ridges and valley of the image. An algorithm based on an a contrario detection is proposed to iteratively compute both of those informations. An orientation field of the tangent to the locally relevant structures is estimated in this algorithm using orientation interpolation techniques. Biological aims include a better understanding of otolith formation and automating tedious tasks such as fish age estimation, of key importance in fish stock management
Pastergue-Ruiz, Isabelle. "La représentation visuelle de l'espace chez un insecte : la fourmi Cataglyphis cursor (Hymenoptera, Formicidae)". Toulouse 3, 1995. http://www.theses.fr/1995TOU30261.
Texto completo da fonteScherrer, Bruno. "Apprentissage de représentation et auto-organisation modulaire pour un agent autonome". Phd thesis, Université Henri Poincaré - Nancy I, 2003. http://tel.archives-ouvertes.fr/tel-00003377.
Texto completo da fonteNous avons considéré trois problèmes de complexité croissante et montré qu'ils admettaient des solutions algorithmiques connexionnistes : 1) L'apprentissage par renforcement dans un petit espace d'états : nous nous appuyons sur un algorithme de la littérature pour construire un réseau connexionniste ; les paramètres du problème sont stockés par les poids des unités et des connexions et le calcul du plan est le résultat d'une activité distribuée dans le réseau. 2) L'apprentissage d'une représentation pour approximer un problème d'apprentissage par renforcement ayant un grand espace d'états : nous automatisons le procédé consistant à construire une partition de l'espace d'états pour approximer un problème de grande taille. 3) L'auto-organisation en modules spécialisés pour approximer plusieurs problèmes d'apprentissage par renforcement ayant un grand espace d'états : nous proposons d'exploiter le principe "diviser pour régner" et montrons comment plusieurs tâches peuvent être réparties efficacement sur un petit nombre de modules fonctionnels spécialisés.
Delteil, Alexandre. "Représentation et apprentissage de concepts et d'ontologies pour le web sémantique". Nice, 2002. http://www.theses.fr/2002NICE5786.
Texto completo da fonteMazard, Angélique. "Bases neurales de l'imagerie mentale visuelle : effet du contenu de l'image mentale et implication de l'aire visuelle primaire". Caen, 2002. http://www.theses.fr/2002CAEN3078.
Texto completo da fonteGoujon, Annabelle. "Apprentissage implicite de régularités contextuelles au cours de l'analyse de scènes visuelles". Aix-Marseille 1, 2007. http://www.theses.fr/2007AIX10099.
Texto completo da fonteBoloix, Emmanuelle. "INFLUENCE DE LA TÂCHE SUR LE TRAITEMENT DES SCÈNES VISUELLES COMPLEXES : UNE MODÉLISATION DES NIVEAUX DE REPRÉSENTATION". Phd thesis, Université de Provence - Aix-Marseille I, 2005. http://tel.archives-ouvertes.fr/tel-00011364.
Texto completo da fonteAissa, Wafa. "Réseaux de modules neuronaux pour un raisonnement visuel compositionnel". Electronic Thesis or Diss., Paris, HESAM, 2023. http://www.theses.fr/2023HESAC033.
Texto completo da fonteThe context of this PhD thesis is compositional visual reasoning. When presented with an image and a question pair, our objective is to have neural networks models answer the question by following a reasoning chain defined by a program. We assess the model's reasoning ability through a Visual Question Answering (VQA) setup.Compositional VQA breaks down complex questions into modular easier sub-problems.These sub-problems include reasoning skills such as object and attribute detection, relation detection, logical operations, counting, and comparisons. Each sub-problem is assigned to a different module. This approach discourages shortcuts, demanding an explicit understanding of the problem. It also promotes transparency and explainability.Neural module networks (NMN) are used to enable compositional reasoning. The framework is based on a generator-executor framework, the generator learns the translation of the question to its function program. The executor instantiates a neural module network where each function is assigned to a specific module. We also design a neural modules catalog and define the function and the structure of each module. The training and evaluations are conducted using the pre-processed GQA dataset cite{gqa}, which includes natural language questions, functional programs representing the reasoning chain, images, and corresponding answers.The research contributions revolve around the establishment of an NMN framework for the VQA task.One primary contribution involves the integration of vision and language pre-trained (VLP) representations into modular VQA. This integration serves as a ``warm-start" mechanism for initializing the reasoning process.The experiments demonstrate that cross-modal vision and language representations outperform uni-modal ones. This utilization enables the capture of intricate relationships within each individual modality while also facilitating alignment between different modalities, consequently enhancing overall accuracy of our NMN.Moreover, we explore various training techniques to enhance the learning process and improve cost-efficiency. In addition to optimizing the modules within the reasoning chain to collaboratively produce accurate answers, we introduce a teacher-guidance approach to optimize the intermediate modules in the reasoning chain. This ensures that these modules perform their specific reasoning sub-tasks without taking shortcuts or compromising the reasoning process's integrity. We propose and implement several teacher-guidance techniques, one of which draws inspiration from the teacher-forcing method commonly used in sequential models. Comparative analyses demonstrate the advantages of our teacher-guidance approach for NMNs, as detailed in our paper [1].We also introduce a novel Curriculum Learning (CL) strategy tailored for NMNs to reorganize the training examples and define a start-small training strategy. We begin by learning simpler programs and progressively increase the complexity of the training programs. We use several difficulty criteria to define the CL approach. Our findings demonstrate that by selecting the appropriate CL method, we can significantly reduce the training cost and required training data, with only a limited impact on the final VQA accuracy. This significant contribution forms the core of our paper [2].[1] W. Aissa, M. Ferecatu, and M. Crucianu. Curriculum learning for compositional visual reasoning. In Proceedings of VISIGRAPP 2023, Volume 5: VISAPP, 2023.[2] W. Aissa, M. Ferecatu, and M. Crucianu. Multimodal representations for teacher-guidedcompositional visual reasoning. In Advanced Concepts for Intelligent Vision Systems, 21st International Conference (ACIVS 2023). Springer International Publishing, 2023.[3] D. A. Hudson and C. D. Manning. GQA: A new dataset for real-world visual reasoning and compositional question answering. 2019
Pétreault-Vailleau, Françoise. "Méthode audio-visuelle et apprentissage de la lecture/écriture par des adolescents migrants". Besançon, 1987. http://www.theses.fr/1987BESA1002.
Texto completo da fontePétreault-Vailleau, Françoise. "Méthode audio-visuelle et apprentissage de la lecture-écriture par des adolescents migrants". Lille 3 : ANRT, 1987. http://catalogue.bnf.fr/ark:/12148/cb37610473w.
Texto completo da fonteReveleau, Aurélien. "Représentation visuelle des sources sonores, des forces d'intéraction et intégration d'une représentation 3D de l'environnement dans une interface de téléopération pour robot mobile". Mémoire, Université de Sherbrooke, 2015. http://hdl.handle.net/11143/6064.
Texto completo da fonteBordes, Patrick. "Deep Multimodal Learning for Joint Textual and Visual Reasoning". Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS370.
Texto completo da fonteIn the last decade, the evolution of Deep Learning techniques to learn meaningful data representations for text and images, combined with an important increase of multimodal data, mainly from social network and e-commerce websites, has triggered a growing interest in the research community about the joint understanding of language and vision. The challenge at the heart of Multimodal Machine Learning is the intrinsic difference in semantics between language and vision: while vision faithfully represents reality and conveys low-level semantics, language is a human construction carrying high-level reasoning. One the one hand, language can enhance the performance of vision models. The underlying hypothesis is that textual representations contain visual information. We apply this principle to two Zero-Shot Learning tasks. In the first contribution on ZSL, we extend a common assumption in ZSL, which states that textual representations encode information about the visual appearance of objects, by showing that they also encode information about their visual surroundings and their real-world frequence. In a second contribution, we consider the transductive setting in ZSL. We propose a solution to the limitations of current transductive approaches, that assume that the visual space is well-clustered, which does not hold true when the number of unknown classes is high. On the other hand, vision can expand the capacities of language models. We demonstrate it by tackling Visual Question Generation (VQG), which extends the standard Question Generation task by using an image as complementary input, by using visual representations derived from Computer Vision
Phenix, Thierry. "Modélisation bayésienne algorithmique de la reconnaissance visuelle de mots et de l'attention visuelle". Thesis, Université Grenoble Alpes (ComUE), 2018. http://www.theses.fr/2018GREAV075/document.
Texto completo da fonteIn this thesis, we propose an original theoretical framework of visual word recognition, and implement it mathematically to evaluate its ability to reproduce experimental observations of the field. A critical review of previous computational models leads us to define specifications in the form of a set of five hypotheses, that form the basis of the proposed theoretical framework: the model is built on a three-layer architecture (sensory, perceptual, lexical); letter processing is parallel; positional coding is distributed; finally, sensory processing involves gaze position, visual acuity, and visual attention distribution. To implement the model, we rely on the Bayesian algorithmic modeling methodology, and define the BRAID model (for "Bayesian word Recognition with Attention, Interference and Dynamics")
Aldea, Emanuel. "Apprentissage de données structurées pour l'interprétation d'images". Paris, Télécom ParisTech, 2009. http://www.theses.fr/2009ENST0053.
Texto completo da fonteImage interpretation methods use primarily the visual features of low-level or high-level interest elements. However, spatial information concerning the relative positioning of these elements is equally beneficial, as it has been shown previously in segmentation and structure recognition. Fuzzy representations permit to assess at the same time the imprecision degree of a relation and the gradual transition between the satisfiability and the non-satisfiability of a relation. The objective of this work is to explore techniques of spatial information representation and their integration in the learning process, within the context of image classifiers that make use of graph kernels. We motivate our choice of labeled graphs for representing images, in the context of learning with SVM classifiers. Graph kernels have been studied intensively in computational chemistry and biology, but an adaptation for image related graphs is necessary, since image structures and properties of the information encoded in the labeling are fundamentally different. We illustrate the integration of spatial information within the graphical model by considering fuzzy adjacency measures between interest elements, and we define a family of graph representations determined by different thresholds applied to these spatial measures. Finally, we employ multiple kernel learning in order to build up classifiers that can take into account different graphical representations of the same image at once. Results show that spatial information complements the visual features of distinctive elements in images and that adapting the discriminative kernel functions for the fuzzy spatial representations is beneficial in terms of performance
Fusty-Raynaud, Sylvie. "Apprentissage et dysfonctionnement du langage écrit et représentation motrice de la parole". Paris 8, 2007. http://octaviana.fr/document/145514919#?c=0&m=0&s=0&cv=0.
Texto completo da fonteData about expert reader, reading learning and reading disabilities lead neither to a homogeneous definition of dyslexics nor a coherent methodology of remediation. This thesis aims to analyse reading learning difficulties in a new way. Rather than considering the good reader's behavior, we examine the constraints imposed and the resources required by alphabetic system. Rather than examine the dyslexic’s characteristics, we observe how the remediation is adapted to the subjects and influences them. The alphabetic system is based on grapheme / phoneme association. The phoneme is defined by articulatory more than acoustic features. Thus, reading is primarily based on speech-motor representation which actively connects visual and auditory representations. Learning disabilities remediation is based on oral realization, which is the active principle of each remediation program, as it enables readers to recognize speech gesture symbolised by graphemes. Thus it appears that the normal readers and not the dyslexics share a cognitive structure which corresponds to the alphabetic system mark, generating an audio-visuo-grapho-phonatory representation of speech
Ziat, Ali Yazid. "Apprentissage de représentation pour la prédiction et la classification de séries temporelles". Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066324/document.
Texto completo da fonteThis thesis deals with the development of time series analysis methods. Our contributions focus on two tasks: time series forecasting and classification. Our first contribution presents a method of prediction and completion of multivariate and relational time series. The aim is to be able to simultaneously predict the evolution of a group of time series connected to each other according to a graph, as well as to complete the missing values in these series (which may correspond for example to a failure of a sensor during a given time interval). We propose to use representation learning techniques to forecast the evolution of the series while completing the missing values and taking into account the relationships that may exist between them. Extensions of this model are proposed and described: first in the context of the prediction of heterogeneous time series and then in the case of the prediction of time series with an expressed uncertainty. A prediction model of spatio-temporal series is then proposed, in which the relations between the different series can be expressed more generally, and where these can be learned.Finally, we are interested in the classification of time series. A joint model of metric learning and time-series classification is proposed and an experimental comparison is conducted
Ziat, Ali Yazid. "Apprentissage de représentation pour la prédiction et la classification de séries temporelles". Electronic Thesis or Diss., Paris 6, 2017. http://www.theses.fr/2017PA066324.
Texto completo da fonteThis thesis deals with the development of time series analysis methods. Our contributions focus on two tasks: time series forecasting and classification. Our first contribution presents a method of prediction and completion of multivariate and relational time series. The aim is to be able to simultaneously predict the evolution of a group of time series connected to each other according to a graph, as well as to complete the missing values in these series (which may correspond for example to a failure of a sensor during a given time interval). We propose to use representation learning techniques to forecast the evolution of the series while completing the missing values and taking into account the relationships that may exist between them. Extensions of this model are proposed and described: first in the context of the prediction of heterogeneous time series and then in the case of the prediction of time series with an expressed uncertainty. A prediction model of spatio-temporal series is then proposed, in which the relations between the different series can be expressed more generally, and where these can be learned.Finally, we are interested in the classification of time series. A joint model of metric learning and time-series classification is proposed and an experimental comparison is conducted
Prudhomme, Elie. "Représentation et fouille de données volumineuses". Thesis, Lyon 2, 2009. http://www.theses.fr/2009LYO20048/document.
Texto completo da fonte/
Guerry, Joris. "Reconnaissance visuelle robuste par réseaux de neurones dans des scénarios d'exploration robotique. Détecte-moi si tu peux !" Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLX080/document.
Texto completo da fonteThe main objective of this thesis is visual recognition for a mobile robot in difficult conditions. We are particularly interested in neural networks which present today the best performances in computer vision. We studied the concept of method selection for the classification of 2D images by using a neural network selector to choose the best available classifier given the observed situation. This strategy works when data can be easily partitioned with respect to available classifiers, which is the case when complementary modalities are used. We have therefore used RGB-D data (2.5D) in particular applied to people detection. We propose a combination of independent neural network detectors specific to each modality (color & depth map) based on the same architecture (Faster RCNN). We share intermediate results of the detectors to allow them to complement and improve overall performance in difficult situations (luminosity loss or acquisition noise of the depth map). We are establishing new state of the art scores in the field and propose a more complex and richer data set to the community (ONERA.ROOM). Finally, we made use of the 3D information contained in the RGB-D images through a multi-view method. We have defined a strategy for generating 2D virtual views that are consistent with the 3D structure. For a semantic segmentation task, this approach artificially increases the training data for each RGB-D image and accumulates different predictions during the test. We obtain new reference results on the SUNRGBD and NYUDv2 datasets. All these works allowed us to handle in an original way 2D, 2.5D and 3D robotic data with neural networks. Whether for classification, detection and semantic segmentation, we not only validated our approaches on difficult data sets, but also brought the state of the art to a new level of performance
Suret-Canale, Michel. "D'un atelier à l'autre : au regard des faits". Paris 1, 1996. http://www.theses.fr/1996PA010641.
Texto completo da fonteThe thesis consists of a critical self-analysis and the clarification of the dialectical relationship (theoretical practical) supporting the artistic work of the author. The aim of this research, formalised by a dialogue between sight and vision, could be resumed as follows : in an image, to show that part which is shadow, the blindness from which one's viewpoint emerges and of which the critical image preserves the memory. The objective, uncertain, is to succed, both through the successive hybridzation of techniques and critical reflection, in the creation of composite images. Composite images, images which attest banally to a ça a été, everyday images that have rid themselves of the strategic stakes of art, free to return to a common ground, not on the grounds of artistic cliche, but rather the common ground of everday life, espace de ressemblement ; because once idle, the image comes to resemble us, to bring us together. Failure is not feared, it appears, to the contrary, to be a necessary condition to the succes of the project
Guarda, Alvaro. "Apprentissage génétique de règles de reconnaissance visuelle : application à la reconnaissance d'éléments du visage". Grenoble INPG, 1998. http://www.theses.fr/1998INPG0110.
Texto completo da fonteArneton, Mélissa. "Bilinguisme et apprentissage des mathématiques : études à la Martinique". Thesis, Nancy 2, 2010. http://www.theses.fr/2010NAN21009/document.
Texto completo da fonteIn this thesis, we try to explain why French overseas pupils have got, for many years, inferior performances to their mainland French school fellows at national academic evaluations. The most surprising is that the observed differences are stronger in mathematics than in French. Then, we focus on the cultural characteristics (bilingualism and collective beliefs) able to influence the school learning, in a French Overseas Department considered as a ?natural laboratory?: Martinique. We carry out four studies with two educational levels (in elementary school and first year of the secondary school). In the first study, we make side analysis of several years' national academic data. They acknowledge the observation as a reality and they invalidate two hypotheses, one to a specific difference in a particular field of mathematics (in geometry for example) and a second relative to an item differential functioning. In the second study, an experimental procedure allows 1) to measure social and cognitive bilingualism of Martinican pupils, 2) to evaluate with different procedures the children performances in mathematics and 3) to collect their scores at national evaluations. This second study refutes the hypothesis of the influence of bilingualism on academic learning. In the third study, we deal with the link between social beliefs (specifically the children?s beliefs of the school disciplines) and their performances. The results do not allow to conclude that the martinican children have worst beliefs of the mathematics than the French mainland children. In the last study, we compile data collected in the precedent analysis, in order to refute the bilingualism?s influence on the school learning. Finally, in the same time, we explain our observations and we submit considered perspectives relatives, for one part, to methodology and the instruments used in this research and, for the second part, to others cultural perspectives, which could be explore