Dissertations / Theses on the topic 'Modèle d'attention'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 15 dissertations / theses for your research on the topic 'Modèle d'attention.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Zhang, Yi. "Implantation d'un modèle d'attention en COGENT." Mémoire, Université de Sherbrooke, 2004. http://savoirs.usherbrooke.ca/handle/11143/4665.
Full textPerreira, Da Silva Matthieu. "Modèle computationnel d'attention pour la vision adaptative." Phd thesis, Université de La Rochelle, 2010. http://tel.archives-ouvertes.fr/tel-00573844.
Full textPerreira, da Silva Matthieu. "Modèle computationnel d'attention pour la vision adaptative." Thesis, La Rochelle, 2010. http://www.theses.fr/2010LAROS317/document.
Full textProviding real time analysis of the huge amount of data generated by computer vision algorithms in interactive applications is still an open problem. It promises great advances across a wide variety of fields : robotics, distance education, or new mouse-less and keyboard-less human computer interaction.When using scene analysis algorithms for computer vision, a trade-off must be found between the quality of the results expected, and the amount of computer resources allocated for each task. It is usually a design time decision, implemented through the choice of pre-defined algorithms and parameters. However, this way of doing limits the generality of the system. Using an adaptive vision system provides a more flexible solution as its analysis strategy can be changed according to the information available concerning the execution context. As a consequence, such a system requires some kind of guiding mechanism to explore the scene faster and more efficiently.In human, the mechanisms of evolution have generated the visual attention system which selects the most important information in order to reduce both cognitive load and scene understanding ambiguity.In this thesis, we propose a visual attention system tailored for interacting with a vision system (whose theoretical architecture is given) so that it adapts its processing according to the interest (or salience) of each element of the scene.Somewhere in between hierarchical salience based (ex: [Koch1985], then [Itti1998]) and competitive distributed (ex: [Desimone1995], then [Deco2004, Rolls2006]) models, we propose a hierarchical yet competitive and non salience based model. Our original approach allows the generation of attentional focus points without the need of neither saliency map nor explicit inhibition of return mechanism. This new real-time computational model is based on a preys / predators system. The use of this kind of dynamical system is justified by an adjustable trade-off between nondeterministic attentional behavior and properties of stability, reproducibility and reactiveness.Our experiments shows that despite the non deterministic behavior of preys / predators equations, the system exhibits interesting properties of stability, reproducibility and reactiveness while allowing a fast and efficient exploration of the scene. These properties are useful for addressing different kinds of applications, ranging from image complexity evaluation, to object detection and tracking. Finally, while it is designed for computer vision, we compare our model to human visual attention. We show that it is equally as plausible as existing models (or better, depending on its configuration)
Ho-Phuoc, Tien. "Développement et mise en œuvre de modèle d'attention visuelle." Grenoble INPG, 2010. https://tel.archives-ouvertes.fr/tel-00495365.
Full textTo explore the world around us, we move constantly our eyes. What factors guide eye movements? How to interpret and evaluate quantitatively them? This thesis addresses these problems in the context of free viewing of natural scenes, according two aspects: modelisation and behavioural data obtained from eye movements experiments. The proposed «bottom-up» model is inspired mainly by the biology of the human visual system and proposes to predict the salient regions (which attract the eyes). We show that although colour is often used in most models in the literature, it influences little on eye movements. It is also unveiled that programming severa 1 saccades in parallel from one fixation point is not compatible with the experimental data
Gautier, Josselin. "Un modèle d'attention visuelle dynamique pour conditions 2D et 3D ; codage de cartes de profondeur et synthèse basée inpainting pour les vidéos multi-vues." Phd thesis, Université Rennes 1, 2012. http://tel.archives-ouvertes.fr/tel-00758112.
Full textChaabouni, Souad. "Etude et prédiction d'attention visuelle avec les outils d'apprentissage profond en vue d'évaluation des patients atteints des maladies neuro-dégénératives." Thesis, Bordeaux, 2017. http://www.theses.fr/2017BORD0768/document.
Full textThis thesis is motivated by the diagnosis and the evaluation of the dementia diseasesand with the aim of predicting if a new recorded gaze presents a complaint of thesediseases. Nevertheless, large-scale population screening is only possible if robust predictionmodels can be constructed. In this context, we are interested in the design and thedevelopment of automatic prediction models for specific visual content to be used in thepsycho-visual experience involving patients with dementia (PwD). The difficulty of sucha prediction lies in a very small amount of training data.Visual saliency models cannot be founded only on bottom-up features, as suggested byfeature integration theory. The top-down component of human visual attention becomesprevalent as human observers explore the visual scene. Visual saliency can be predictedon the basis of seen data. Deep Convolutional Neural Networks (CNN) have proven tobe a powerful tool for prediction of salient areas in static images. In order to constructan automatic prediction model for the salient areas in natural and intentionally degradedvideos, we have designed a specific CNN architecture. To overcome the lack of learningdata we designed a transfer learning scheme derived from bengio’s method. We measureits performances when predicting salient regions. The obtained results are interestingregarding the reaction of normal control subjects against degraded areas in videos. Thepredicted saliency map of intentionally degraded videos gives an interesting results comparedto gaze fixation density maps and other reference models
Muddamsetty, Satya Mahesh. "Modèles d'attention visuelle pour l'analyse de scènes dynamiques." Thesis, Dijon, 2014. http://www.theses.fr/2014DIJOS067/document.
Full textVisual saliency is an important research topic in the field of computer vision due to its numerouspossible applications. It helps to focus on regions of interest instead of processingthe whole image or video data. Detecting visual saliency in still images has been widelyaddressed in literature with several formulations. However, visual saliency detection invideos has attracted little attention, and is a more challenging task due to additional temporalinformation. Indeed, a video contains strong spatio-temporal correlation betweenthe regions of consecutive frames, and, furthermore, motion of foreground objects dramaticallychanges the importance of the objects in a scene. The main objective of thethesis is to develop a spatio-temporal saliency method that works well for complex dynamicscenes.A spatio-temporal saliency map is usually obtained by the fusion of a static saliency mapand a dynamic saliency map. In our work, we model the dynamic textures in a dynamicscene with Local Binary Patterns (LBP-TOP) to compute the dynamic saliency map, andwe use color features to compute the static saliency map. Both saliency maps are computedusing a bio-inspired mechanism of Human Visual System (HVS) with a discriminantformulation known as center surround saliency, and are fused in a proper way.The proposed models have been extensively evaluated with diverse publicly availabledatasets which contain several videos of dynamic scenes. The evaluation is performed intwo parts. First, the method in locating interesting foreground objects in complex scene.Secondly, we evaluate our model on the task of predicting human observers fixations.The proposed method is also compared against state-of-the art methods, and the resultsshow that the proposed approach achieves competitive results.In this thesis we also evaluate the performance of different fusion techniques, because fusionplays a critical role in the accuracy of the spatio-temporal saliency map. We evaluatethe performances of different fusion techniques on a large and diverse complex datasetand the results show that a fusion method must be selected depending on the characteristics,in terms of color and motion contrasts, of a sequence. Overall, fusion techniqueswhich take the best of each saliency map (static and dynamic) in the final spatio-temporalmap achieve best results
Botterman, Hông-Lan. "Corrélations dans les graphes d'information hétérogène : prédiction et modélisation de liens à partir de méta-chemins." Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS083.
Full textMany entities, possibly of different natures, are linked by physical or virtual links, that may also be of different natures. Such data can be represented by a heterogeneous information network (HIN). In addition, there are often correlations between real-life entities or events. Once represented by suitable abstractions (such as HIN), these correlations can therefore be found in the HIN. Motivated by these considerations, this thesis investigates the effects of possible correlations between the links of an HIN on its structure. This present work aims at answering questions such as: are there indeed correlations between different types of links? If so, is it possible to quantify them? What do they mean? How can they be interpreted? Can these correlations be used to predict the occurrence of links? To model co-evolution dynamics? The examples studied can be divided into two categories. First, the use of correlations for the prediction of the links’ weight is studied. It is shown that correlations between links, and more specifically between paths, can be used to recover and, to some extent, predict the weight of other links of a specified type. Second, a link weight dynamics is considered. It is shown that link co-evolution can be used, for example, to define a model of attention between individuals and subjects. The preliminary results are in agreement with others in the literature, mainly related to models of opinion dynamics. Overall, this work illustrates the importance of correlations between the links of an HIN. In addition, it supports the general fact that different types of nodes and links abound in nature and that it could be important and instructive to take this diversity into account in order to understand the organization and functioning of a system
Martinez, Francis. "Tout est dans le regard : reconnaissance visuelle du comportement humain en vue subjective." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2013. http://tel.archives-ouvertes.fr/tel-01001816.
Full textHillaire, Sébastien. "Contribution à l'étude des modèles d'attention visuelle et du suivi de regard pour améliorer le retour visuel dans les applications 3D interactives." Rennes, INSA, 2011. http://www.theses.fr/2011ISAR0002.
Full textIn virtual reality, the interaction between a human and a computer can be achieved through multiple sensory channels. The visual channel is generally used in order to provide a visual feedback to the user interacting with a virtual environment. The goal of this thesis is to improve this visual feedback by taking into account user’s visual attention in an interactive manner. The first part of this thesis is dedicated to human attention. We wanted to evaluate in real-time the gaze point of a user navigating in a 3D virtual environment using a first-person view. We have first studied human visual attention when walking in a virtual environment and have shown that there are several common behaviors when compared to a real pedestrian walk. We have then proposed a model in order to simulate this behavior. We have included this component in a novel visual attention model able to predict, in real-time, the attention of a user navigating in a virtual environment. Our evaluation has shown that our model was able to predict the users' visual attention more efficiently than existing models. Finally, we have proposed a novel use of visual attention models in order to improve the accuracy of any gaze tracking systems. Our study has shown that our approach could improve the global accuracy of these systems. In the second part of this thesis, we have researched a novel way to improve the visual feedback to the users in order to improve their immersion feelings and perception of a virtual environment. We have proposed a novel use of the gaze point in order to simulate natural visual effects present in human vision: a depth-of-field blur effect and a compensated camera motion. Our study has shown that these effects were strongly preferred by participants when they were computed based on their gaze point, in a more interactive manner
Belkacem, Thiziri. "Neural models for information retrieval : towards asymmetry sensitive approaches based on attention models." Thesis, Toulouse 3, 2019. http://www.theses.fr/2019TOU30167.
Full textThis work is situated in the context of information retrieval (IR) using machine learning (ML) and deep learning (DL) techniques. It concerns different tasks requiring text matching, such as ad-hoc research, question answering and paraphrase identification. The objective of this thesis is to propose new approaches, using DL methods, to construct semantic-based models for text matching, and to overcome the problems of vocabulary mismatch related to the classical bag of word (BoW) representations used in traditional IR models. Indeed, traditional text matching methods are based on the BoW representation, which considers a given text as a set of independent words. The process of matching two sequences of text is based on the exact matching between words. The main limitation of this approach is related to the vocabulary mismatch. This problem occurs when the text sequences to be matched do not use the same vocabulary, even if their subjects are related. For example, the query may contain several words that are not necessarily used in the documents of the collection, including relevant documents. BoW representations ignore several aspects about a text sequence, such as the structure the context of words. These characteristics are important and make it possible to differentiate between two texts that use the same words but expressing different information. Another problem in text matching is related to the length of documents. The relevant parts can be distributed in different ways in the documents of a collection. This is especially true in large documents that tend to cover a large number of topics and include variable vocabulary. A long document could thus contain several relevant passages that a matching model must capture. Unlike long documents, short documents are likely to be relevant to a specific subject and tend to contain a more restricted vocabulary. Assessing their relevance is in principle simpler than assessing the one of longer documents. In this thesis, we have proposed different contributions, each addressing one of the above-mentioned issues. First, in order to solve the problem of vocabulary mismatch, we used distributed representations of words (word embedding) to allow a semantic matching between the different words. These representations have been used in IR applications where document/query similarity is computed by comparing all the term vectors of the query with all the term vectors of the document, regardless. Unlike the models proposed in the state-of-the-art, we studied the impact of query terms regarding their presence/absence in a document. We have adopted different document/query matching strategies. The intuition is that the absence of the query terms in the relevant documents is in itself a useful aspect to be taken into account in the matching process. Indeed, these terms do not appear in documents of the collection for two possible reasons: either their synonyms have been used or they are not part of the context of the considered documents. The methods we have proposed make it possible, on the one hand, to perform an inaccurate matching between the document and the query, and on the other hand, to evaluate the impact of the different terms of a query in the matching process. Although the use of word embedding allows semantic-based matching between different text sequences, these representations combined with classical matching models still consider the text as a list of independent elements (bag of vectors instead of bag of words). However, the structure of the text as well as the order of the words is important. Any change in the structure of the text and/or the order of words alters the information expressed. In order to solve this problem, neural models were used in text matching
Elbayad, Maha. "Une alternative aux modèles neuronaux séquence-à-séquence pour la traduction automatique." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM012.
Full textIn recent years, deep learning has enabled impressive achievements in Machine Translation.Neural Machine Translation (NMT) relies on training deep neural networks with large number of parameters on vast amounts of parallel data to learn how to translate from one language to another.One crucial factor to the success of NMT is the design of new powerful and efficient architectures. State-of-the-art systems are encoder-decoder models that first encode a source sequence into a set of feature vectors and then decode the target sequence conditioning on the source features.In this thesis we question the encoder-decoder paradigm and advocate for an intertwined encoding of the source and target so that the two sequences interact at increasing levels of abstraction. For this purpose, we introduce Pervasive Attention, a model based on two-dimensional convolutions that jointly encode the source and target sequences with interactions that are pervasive throughout the network.To improve the efficiency of NMT systems, we explore online machine translation where the source is read incrementally and the decoder is fed partial contexts so that the model can alternate between reading and writing. We investigate deterministic agents that guide the read/write alternation through a rigid decoding path, and introduce new dynamic agents to estimate a decoding path for each sample.We also address the resource-efficiency of encoder-decoder models and posit that going deeper in a neural network is not required for all instances.We design depth-adaptive Transformer decoders that allow for anytime prediction and sample-adaptive halting mechanisms to favor low cost predictions for low complexity instances and save deeper predictions for complex scenarios
Duran, Audrey. "Intelligence artificielle pour la caractérisation du cancer de la prostate par agressivité en IRM multiparamétrique." Thesis, Lyon, 2022. http://theses.insa-lyon.fr/publication/2022LYSEI008/these.pdf.
Full textProstate cancer (PCa) is the most frequently diagnosed cancer in men in more than half the countries in the world and the fifth leading cause of cancer death among men in 2020. Diagnosis of PCa includes multiparametric magnetic resonance imaging acquisition (mp-MRI) - which combines T2 weighted (T2-w), diffusion weighted imaging (DWI) and dynamic contrast enhanced (DCE) sequences - prior to any biopsy. The joint analysis of these multimodal images is time demanding and challenging, especially when individual MR sequences yield conflicting findings. In addition, the sensitivity of MRI is low for less aggressive cancers and inter-reader reproducibility remains moderate at best. Moreover, visual analysis does not currently allow to determine the cancer aggressiveness, characterized by the Gleason score (GS). This is why computer-aided diagnosis (CAD) systems based on statistical learning models have been proposed in recent years, to assist radiologists in their diagnostic task, but the vast majority of these models focus on the binary detection of clinically significant (CS) lesions. The objective of this thesis is to develop a CAD system to detect and segment PCa on mp-MRI images but also to characterize their aggressiveness, by predicting the associated GS. In a first part, we present a supervised CAD system to segment PCa by aggressiveness from T2-w and ADC maps. This end-to-end multi-class neural network jointly segments the prostate gland and cancer lesions with GS group grading. The model was trained and validated with a 5-fold cross-validation on a heterogeneous series of 219 MRI exams acquired on three different scanners prior prostatectomy. Regarding the automatic GS group grading, Cohen’s quadratic weighted kappa coefficient (κ) is 0.418 ± 0.138, which is the best reported lesion-wise kappa for GS segmentation to our knowledge. The model has also encouraging generalization capacities on the PROSTATEx-2 public dataset. In a second part, we focus on a weakly supervised model that allows the inclusion of partly annotated data, where the lesions are identified by points only, for a consequent saving of time and the inclusion of biopsy-based databases. Regarding the automatic GS group grading on our private dataset, we show that we can approach performance achieved with the baseline fully supervised model while considering 6% of annotated voxels only for training. In the last part, we study the contribution of DCE MRI, a sequence often omitted as input to deep models, for the detection and characterization of PCa. We evaluate several ways to encode the perfusion from the DCE MRI information in a U-Net like architecture. Parametric maps derived from DCE MR exams are shown to positively impact segmentation and grading performance of PCa lesions
Ho, Phuoc Tien. "Développement et mise en oeuvre de modèles d'attention visuelle." Phd thesis, 2010. http://tel.archives-ouvertes.fr/tel-00495365.
Full textArchambault, Kim. "Déficit d'attention et tabagisme : mise à l'épreuve d'un modèle médiationnel hypothétique impliquant la réussite scolaire et l'affiliation à des pairs déviants." Thèse, 2007. http://hdl.handle.net/1866/7850.
Full text