Descripteur
Documents disponibles dans cette catégorie (498)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Connecting images through time and sources: Introducing low-data, heterogeneous instance retrieval / Dimitri Gominski (2021)
Titre : Connecting images through time and sources: Introducing low-data, heterogeneous instance retrieval Type de document : Article/Communication Auteurs : Dimitri Gominski , Auteur ; Valérie Gouet-Brunet , Auteur ; Liming Chen, Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2021 Projets : Alegoria / Gouet-Brunet, Valérie Importance : 5 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] base de données d'images
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] descripteur
[Termes IGN] données d'entrainement (apprentissage automatique)
[Termes IGN] données hétérogènes
[Termes IGN] exploration de données
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] image multi sources
[Termes IGN] indexation sémantique
[Termes IGN] précision de la classification
[Termes IGN] recherche d'image basée sur le contenuRésumé : (auteur) With impressive results in applications relying on feature learning, deep learning has also blurred the line between algorithm and data. Pick a training dataset, pick a backbone network for feature extraction, and voilà; this usually works fora variety of use cases. But the underlying hypothesis that there exists a training dataset matching the use case is not alwaysmet. Moreover, the demand for interconnections regardless of the variations of the content calls for increasing generalization and robustness in features. An interesting application characterized by these problematics is the connection of historical and cultural databases of images.Through the seemingly simple task of instance retrieval, wepropose to show that it is not trivial to pick features respondingwell to a panel of variations and semantic content. Introducing anew enhanced version of the ALEGORIA benchmark, we compare descriptors using the detailed annotations. We further give in sights about the core problems in instance retrieval, testing fourstate-of-the-art additional techniques to increase performance. Numéro de notice : P2021-001 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE Nature : Preprint nature-HAL : Préprint DOI : 10.48550/arXiv.2103.10729 Date de publication en ligne : 21/03/2021 En ligne : https://doi.org/10.48550/arXiv.2103.10729 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97398 Consolidation of crowd-sourced geo-ragged data for parameterized travel recommendations / Ago Luberg (2021)
Titre : Consolidation of crowd-sourced geo-ragged data for parameterized travel recommendations Type de document : Thèse/HDR Auteurs : Ago Luberg, Auteur ; Tanel Tammet, Directeur de thèse Editeur : Tallinn [Estonia] : Tallinn University of Technology Année de publication : 2021 Importance : 159 p. Format : 21 x 30 cm Note générale : bibliographie
Dissertation accepted for the defence of the degree of Doctor of Philosophy in Computer ScienceLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web
[Termes IGN] apprentissage automatique
[Termes IGN] base de données
[Termes IGN] conception orientée utilisateur
[Termes IGN] données localisées des bénévoles
[Termes IGN] extraction de données
[Termes IGN] géoréférencement
[Termes IGN] point d'intérêt
[Termes IGN] Riga
[Termes IGN] site wiki
[Termes IGN] système de recommandation
[Termes IGN] Tallinn
[Termes IGN] taxinomie
[Termes IGN] tourismeRésumé : (auteur) The research covered in this thesis is focused on different aspects of the task of creating automated recommendations for tourism, focusing mostly on places of interest like beautiful views, architectural landmarks, charming areas etc. A significant amount of work has been spent on designing and developing actual recommender systems - Sightsplanner, Sightsmap and the automated recommender of Visit Estonia - and their data harvesting methods in order to create a platform for showing the feasibility of the new methods designed and experimented with. The main results of our research are split between three subfields:
• Knowledge engineering: we have shown how to formalize fuzzy and uncertain POI categories along with suitable ontologies and reasoner-based algorithms for object matching and score calculation in a real-life context of actual POI-s, available data and easily expressable user preferences.
• Machine learning: we have designed a learnable detection system for detecting duplicate POIs from different databases, usable for cross- category, cross-language and cross-city datasets.
• We show that learning on Tallinn eateries improved the algorithm parameters to such a degree that on Riga data containing also museums and galleries it gave us 98% accuracy versus 85% accuracy achieved by tuning the algorithm parameters manually.
• Knowledge extraction: we have designed an algorithm for high-quality keyword extraction from short crowd-sourced POI descriptions in different languages, able to find a suitable name and to add suitable types to the POI. Our clusterization algorithm is able to merge the POIs based on the extracted data: on the Panoramio and Wikipedia data about U.K. and French locations it was able to find 56% of Wikipedia objects from the textual titles/annotations of Panoramio pictures in the area.Note de contenu : 1- Introduction
2- Related work
3- Involvement in recommender projects
4- Data acquisition and information extraction
5- Data deduplication (using machine learning)
6- Location category and name detection
7- Data storage and object score calculation
8- Conclusions
9- Future workNuméro de notice : 28600 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Thèse étrangère Note de thèse : PhD Thesis : Computer Science : Tallinn University of Technology : 2021 DOI : 10.23658/taltech.23/2021 En ligne : https://doi.org/10.23658/taltech.23/2021 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99407
Titre : Context-aware image super-resolution using deep neural networks Type de document : Thèse/HDR Auteurs : Mohammad Saeed Rad, Auteur ; Jean-Philippe Thiran, Directeur de thèse Editeur : Lausanne : Ecole Polytechnique Fédérale de Lausanne EPFL Année de publication : 2021 Importance : 148 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse présentée pour l'obtention du grade de Docteur ès SciencesLangues : Français (fre) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] image à basse résolution
[Termes IGN] image à haute résolution
[Termes IGN] pouvoir de résolution spectrale
[Termes IGN] reconstruction d'image
[Termes IGN] réseau antagoniste génératif
[Termes IGN] segmentation sémantique
[Termes IGN] vision par ordinateurIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Image super-resolution is a classic ill-posed computer vision and image processing problem, addressing the question of how to reconstruct a high-resolution image from its low-resolution counterpart. Current state-of-the-art methods have improved the performance of the single image super-resolution task significantly by benefiting from machine learning and AI-powered algorithms, and more specifically, with the advent of Deep Learning-based approaches. Although these advances allow a machine to learn and have better exploitation of an image and its content, recent methods are still unable to constrain the plausible solution space based on the available contextual information within an image. This limitation mostly results in poor reconstructions, even for well-known types of objects and textures easily recognizable for humans. In this thesis, we aim at proving that the categorical prior, which characterizes the semantic class of a region in an image (e.g., sky, building, plant), is crucial in super-resolution task for reaching a higher reconstruction quality. In particular, we propose several approaches to improve the perceived image quality and generalization capability of deep learning-based methods by exploiting the context and semantic meaning of images. To prove the effectiveness of this categorical information, we first propose a convolutional neural network-based framework that is able to extract and use semantic information to super-resolve a given image by using multitask learning, simultaneously for learning image super-resolution and semantic segmentation. The proposed decoder is forced to explore categorical information during training, as this setting employs only one shared deep network for both semantic segmentation and super-resolution tasks. We further investigate the possibility of using semantic information by a novel objective function to introduce additional spatial control over the training process. We propose penalizing images at different semantic levels using appropriate loss terms by benefiting from our new OBB (Object, Background, and Boundary) labels generated from segmentation labels. Then, we introduce a new test time adaptation-based technique to leverage high-resolution images with perceptually similar context to a given test image to improve the reconstruction quality. We further validate this approach's effectiveness by using a novel numerical experiment analyzing the correlation between filters learned by our network and what we define as `ideal' filters. Finally, we present a generic solution to enable adapting all our previous contributions in this thesis, as well as other recent super-resolution works trained on synthetic datasets, to real-world super-resolution problem. Real-world super-resolution refers to super-resolving images with real degradations caused by physical imaging systems, instead of low-resolution images from simulated datasets assuming a simple and uniform degradation model (i.e., bicubic downsampling). We study and develop an image-to-image translator to map the distribution of real low-resolution images to the well-understood distribution of bicubically downsampled images. This translator is used as a plug-in to integrate real inputs into any super-resolution framework trained on simulated datasets. We carry out extensive qualitative and quantitative experiments for each mentioned contribution, including user studies, to compare our proposed approaches to state-of-the-art method. Note de contenu : 1- Introduction
2- Brief image super-resolution review
3- Extracting image context by multi-task learning
4- Spatial control over image genertion process
5- Test-time adaptation based on perceptual similarity
6- Integrating into real-world SR
7- ConclusionNuméro de notice : 28652 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse étrangère Note de thèse : Thèse de Doctorat : Sciences : EPFL, Lausanne : 2021 DOI : sans En ligne : https://infoscience.epfl.ch/record/286804?ln=fr Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99790 Contributions to graph-based hierarchical analysis for images and 3D point clouds / Leonardo Gigli (2021)
Titre : Contributions to graph-based hierarchical analysis for images and 3D point clouds Type de document : Thèse/HDR Auteurs : Leonardo Gigli, Auteur ; Beatriz Marcotegui, Directeur de thèse Editeur : Paris : Université Paris Sciences et Lettres Année de publication : 2021 Importance : 177 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse de Doctorat de l'Université PSL, Spécialité : Morphologie MathématiqueLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] analyse de groupement
[Termes IGN] apprentissage automatique
[Termes IGN] arbre aléatoire minimum
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] extraction du réseau routier
[Termes IGN] morphologie mathématique
[Termes IGN] processus de hiérarchisation analytique
[Termes IGN] réseau neuronal de graphes
[Termes IGN] segmentation d'image
[Termes IGN] semis de points
[Termes IGN] texture d'image
[Termes IGN] théorie des graphesIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Graphs are powerful mathematical structures representing a set of objects and the underlying links between pairs of objects somehow related. They are becoming increasingly popular in data science in general and in particular in image or 3D point cloud analysis. Among the wide spectra of applications, they are involved in most of the hierarchical approaches.Hierarchies are particularly important because they allow us to efficiently organize the information required and to analyze the problems at different levels of detail. In this thesis, we address the following topics. Many morphological hierarchical approaches rely on the Minimum Spanning Tree (MST). We propose an algorithm for MST computation in streaming based on a graph decomposition strategy. Thanks to this decomposition, larger images can be processed or can benefit from partial reliable information while the whole image is not completely available.Recent LiDAR developments are able to acquire large-scale and precise 3D point clouds. Many applications, such as infrastructure monitoring, urban planning, autonomous driving, precision forestry, environmental assessment, archaeological discoveries, to cite a few, are under development nowadays. We introduce a ground detection algorithm and compare it with the state of the art. The impact of reducing the point cloud density with low-cost scanners is studied, in the context of an autonomous driving application. Finally, in many hierarchical methods similarities between points are given as input. However, the metric used to compute similarities influences the quality of the final results. We exploit metric learning as a complementary tool that helps to improve the quality of hierarchies. We demonstrate the capabilities of these methods in two contexts. The first one,a texture classification of 3D surfaces. Our approach ranked second in a task organized by SHREC’20 international challenge. The second one learning the similarity function together with the optimal hierarchical clustering, in a continuous feature-based hierarchical clustering formulation. Note de contenu : Introduction
1- Graph theory and clustering
2- Point clouds
3- Ground and road detection
4- Minimum spanning tree for data streams
5- Metric learning
6- Towards Morphological Convolutions on Graphs
ConclusionsNuméro de notice : 28623 Affiliation des auteurs : non IGN Thématique : IMAGERIE/MATHEMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Morphologie Mathématique : Paris Sciences et Lettres : 2021 Organisme de stage : Centre de Morphologie Mathématique DOI : sans En ligne : https://pastel.hal.science/tel-03512298/ Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99543
Titre : Data mining : methods, applications and systems Type de document : Monographie Auteurs : Derya Birant, Éditeur scientifique Editeur : London [UK] : IntechOpen Année de publication : 2021 Importance : 200 p. ISBN/ISSN/EAN : 978-1-83968-319-0 Note générale : Print ISBN 978-1-83968-318-3
eBook (PDF) ISBN 978-1-83968-320-6Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] acquisition de données
[Termes IGN] apprentissage profond
[Termes IGN] arbre de décision
[Termes IGN] exploration de données
[Termes IGN] Python (langage de programmation)
[Termes IGN] série temporelleIndex. décimale : 26.40 Intelligence artificielle Résumé : (Editeur) Data mining is a branch of computer science that is used to automatically extract meaningful, useful knowledge and previously unknown, hidden, interesting patterns from a large amount of data to support the decision-making process. This book presents recent theoretical and practical advances in the field of data mining. It discusses a number of data mining methods, including classification, clustering, and association rule mining. This book brings together many different successful data mining studies in various areas such as health, banking, education, software engineering, animal science, and the environment. Note de contenu :
1. Deep Learning: Exemplar Studies in Natural Language Processing and Computer Vision / Selma Tekir and Yalin Bastanlar
2. Contribution to Decision Tree Induction with Python: A Review / Bouchra Lamrini
3. Association Rule Mining on Big Data Sets / Oguz Celik, Muruvvet Hasanbasoglu, Mehmet S. Aktas and Oya Kalipsiz
4. Data Mining in Banking Sector Using Weighted Decision Jungle Method / Derya Birant
5. Analytical Statistics Techniques of Classification and Regression in Machine Learning / Pramod Kumar, Sameer Ambekar, Manish Kumar and Subarna Roy
6. Clustering of Time-Series Data / Esma Ergüner Özkoç
7. Weather Nowcasting Using Deep Learning Techniques / Makhamisa Senekane, Mhlambululi Mafu and Molibeli Benedict Taele
8. Data Mining and Machine Learning for Software Engineering / Elife Ozturk Kiyak
9. Data Mining for Student Performance Prediction in Education / Ferda Ünal
10. Tracer Transport in a Homogeneous Porous Medium: Experimental Study and Acquisition Data with LabVIEW / Sana Dardouri and Jalila Sghaier
11. Data Mining and Fuzzy Data Mining Using MapReduce Algorithms / Poli Venkata Subba ReddyNuméro de notice : 26539 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE Nature : Recueil / ouvrage collectif DOI : 10.5772/intechopen.87784 En ligne : http://doi.org/10.5772/intechopen.87784 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97753 Deep convolutional neural networks for scene understanding and motion planning for self-driving vehicles / Abdelhak Loukkal (2021)PermalinkPermalinkDeep learning for wildfire progression monitoring using SAR and optical satellite image time series / Puzhao Zhang (2021)PermalinkDescription et recherche d’image généralisables pour l’interconnexion et l’analyse multi-source / Dimitri Gominski (2021)PermalinkDétection d’ouvertures par segmentation sémantique de nuages de points 3D : apport de l’apprentissage profond / Camille Lhenry (2021)PermalinkDétection/reconnaissance d'objets urbains à partir de données 3D multicapteurs prises au niveau du sol, en continu / Younes Zegaoui (2021)PermalinkDétection et reconstruction 3D d’arbres urbains par segmentation de nuages de points : apport de l’apprentissage profond / Victor Alteirac (2021)PermalinkDynamic committee machine with fuzzy-c-means clustering for total organic carbon content prediction from wireline logs / Yang Bai in Computers & geosciences, vol 146 (January 2021)PermalinkEvaluation of a neural network with uncertainty for detection of ice and water in SAR imagery / Nazanin Asadi in IEEE Transactions on geoscience and remote sensing, vol 59 n° 1 (January 2021)PermalinkExploration of reinforcement learning algorithms for autonomous vehicle visual perception and control / Florence Carton (2021)Permalink