Descripteur
Termes IGN > mathématiques > analyse mathématique > topologie > théorie des graphes > noeud
noeudSynonyme(s)point nodalVoir aussi |
Documents disponibles dans cette catégorie (55)
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
Titre : Analyzing and improving Graph Neural Networks Type de document : Thèse/HDR Auteurs : Guillaume Renton, Auteur ; Sébastien Adam, Auteur Editeur : Université de Rouen Année de publication : 2021 Importance : 130 p. Format : 21 x 30 cm Note générale : bibliographie
Thèse présentée pour obtenir le diplôme de Doctorat de l'Université de Rouen Normandie, spécialité InformatiqueLangues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle
[Termes IGN] apprentissage profond
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] filtre passe-bande
[Termes IGN] filtre spectral
[Termes IGN] noeud
[Termes IGN] réseau neuronal de graphes
[Termes IGN] théorie des graphes
[Termes IGN] transformation de Laplace
[Termes IGN] transformation inverseIndex. décimale : THESE Thèses et HDR Résumé : (auteur) Although theorised about fifteen years ago, the scientific community’s interest for graph neural networks has only really taken off recently. Those models aim to transpose the representation learning capacity inherent in deep neural network onto graph data, via the learning of hidden states associated with the graph nodes. These hidden states are computed and updated according to the information contained in the neighborhoud of each node.This recent interest for graph neural networks (GNNs) has led to a "jungle" of models and frameworks, making this field of research sometimes confusing. Historically, two main strategies have been explored : the spatial GNNs on one side and the spectral GNNs on the other side. Spatial GNNs, sometimes also called Message Passing Neural Network, are based on the computation of a message which agregates the information contained in the neighborhoud of each node. On the other side, spectral GNNs are based on the spectral graph theory and thus on the graph Laplacian. The eigendecomposition of the graph Laplacian allows to define a graph Fourier transform and its inverse. From these transforms, different filters can be applied on the graph, leading to similar result than filtering on images or signals. In this thesis, we begin by introducing a third category, called spectral rooted spatial convolution. Indeed, some recent methods are taking root in the spectral domain while avoiding to compute the eigendecomposition of the graph Laplacian. This third category leads to question about the fundamental difference between spectral and spatial GNNs. We answer this question by proposing a general model unifying both strategies, showing notably that spectral GNNs are a particular case of spatial GNNs. This unified model also allowed us to propose a spectral analysis of some popular GNNs in the scientificcommunitic, namely GCN, GIN, GAT, ChebNet and CayleyNet. This analysis shows that spatial models are limited to low-pass and high-pass filtering, while spectral models can produce any kind of filters. Those results are then found with the presentation of a toy problem, showing in the first instance the limitation of spatial models to define pass-band filters, and the importance of designing such filters. Those results have led us to propose a method allowing any kind of filter, while limiting the network’s number of parameters. Indeed, even though spectral models are able to design any kind of filtering, each new filter require the add of a new weight matrix in the neural network. In order to reduce the number of parameters, we propose to adapt Depthwise Separable Convolution to graphs through a method called Depthwise Separable Graph Convolution Network. This method is evaluated on both transductive and inductive learning, outperforming state-of-the-arts results.Finally, we propose a method defined in the spatial domain in order to take into account edge attributes. Indeed, this issue has been little studied by the scientific community, and the number of methods allowing to include edge attributes is very small. Our proposal, called Edge Embedding Graph Neural Network, consists in embedding edge attributes into a new space through a first neural network, before using the extracted features in a GNN. This method is evaluated on a particular problem of symbol detection in a graph. Note de contenu : 1- Introduction
2- Background
3- What is a Graph Neural Network ?
4- Graph Neural Networks: Are they Spectral or Spatial ?
5- Depthwise Separable Graph Convolution Network
6- Edge Embedding Graph Neural Network
7- ConclusionNuméro de notice : 15259 Affiliation des auteurs : non IGN Thématique : INFORMATIQUE/MATHEMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Informatique : Rouen : 2021 Organisme de stage : Laboratoire LITIS DOI : sans En ligne : https://tel.hal.science/tel-03346018/ Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100612 Learning embeddings for cross-time geographic areas represented as graphs / Margarita Khokhlova (2021)
Titre : Learning embeddings for cross-time geographic areas represented as graphs Type de document : Article/Communication Auteurs : Margarita Khokhlova , Auteur ; Nathalie Abadie , Auteur ; Valérie Gouet-Brunet , Auteur ; Liming Chen, Auteur Editeur : New York [Etats-Unis] : Association for computing machinery ACM Année de publication : 2021 Projets : Alegoria / Gouet-Brunet, Valérie Conférence : SAC 2021, 36th Annual ACM Symposium on Applied Computing 22/03/2021 26/03/2021 en ligne Proceedings ACM Importance : pp 559 - 568 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] arête
[Termes IGN] classification par réseau neuronal
[Termes IGN] entité géographique
[Termes IGN] graphe flou
[Termes IGN] image aérienne à axe vertical
[Termes IGN] noeud
[Termes IGN] relation spatiale
[Termes IGN] représentation graphique
[Termes IGN] réseau neuronal de graphesRésumé : (auteur) Geographic entities from the vertical aerial images can be viewed as discrete objects and represented as nodes in a graph, linked to each other by edges capturing their spatial relationships. Over time, the natural and man made landscape may evolve and thus also their graph representations. This paper addresses the challenging problem of the retrieval and fuzzy matching of graphs to localize near-identical geographical areas across time. Several use-case scenarios are proposed for the end-to-end learning of a graph embedding using Graph Neural Networks (GNN), along with an effective baseline without learning. The results demonstrate the efficiency of our approach, that enables efficient similarity reasoning for novel hand-engineered cross-time graph data. Code and data processing scripts are available online. Numéro de notice : C2021-002 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1145/3412841.3441936 En ligne : https://doi.org/10.1145/3412841.3441936 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97583 A novel orthoimage mosaic method using a weighted A∗ algorithm : Implementation and evaluation / Maoteng Zheng in ISPRS Journal of photogrammetry and remote sensing, vol 138 (April 2018)
[article]
Titre : A novel orthoimage mosaic method using a weighted A∗ algorithm : Implementation and evaluation Type de document : Article/Communication Auteurs : Maoteng Zheng, Auteur ; Xiong Xiaodong, Auteur ; Junfeng Zhu, Auteur Année de publication : 2018 Article en page(s) : pp 30 - 46 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Orthophotographie, orthoimage
[Termes IGN] diagramme de Voronoï
[Termes IGN] drone
[Termes IGN] jeu de données localisées
[Termes IGN] modèle numérique de surface
[Termes IGN] noeud
[Termes IGN] orthophotoplan numérique
[Termes IGN] pondérationRésumé : (Auteur) The implementation and evaluation of a weighted A∗ algorithm for orthoimage mosaic with UAV (Unmanned Aircraft Vehicle) imagery is proposed. The initial seam-line network is firstly generated by standard Voronoi Diagram algorithm; an edge diagram is generated based on DSM (Digital Surface Model) data; the vertices (conjunction nodes of seam-lines) of the initial network are relocated if they are on high objects (buildings, trees and other artificial structures); and the initial seam-lines are refined using the weighted A∗ algorithm based on the edge diagram and the relocated vertices. Our method was tested with three real UAV datasets. Two quantitative terms are introduced to evaluate the results of the proposed method. Preliminary results show that the method is suitable for regular and irregular aligned UAV images for most terrain types (flat or mountainous areas), and is better than the state-of-the-art method in both quality and efficiency based on the test datasets. Numéro de notice : A2018-119 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.02.007 Date de publication en ligne : 09/03/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.02.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89588
in ISPRS Journal of photogrammetry and remote sensing > vol 138 (April 2018) . - pp 30 - 46[article]Exemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2018041 RAB Revue Centre de documentation En réserve L003 Disponible 081-2018043 DEP-EXM Revue LASTIG Dépôt en unité Exclu du prêt 081-2018042 DEP-EAF Revue Nancy Dépôt en unité Exclu du prêt Multi-view performance capture of surface details / Nadia Robertini in International journal of computer vision, vol 124 n° 1 (August 2017)
[article]
Titre : Multi-view performance capture of surface details Type de document : Article/Communication Auteurs : Nadia Robertini, Auteur ; Dan Casas, Auteur ; Edilson De Aguiar, Auteur ; Christian Theobalt, Auteur Année de publication : 2017 Article en page(s) : pp 96 – 113 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] courbe de Gauss
[Termes IGN] échelle d'intensité
[Termes IGN] image numérique
[Termes IGN] image vidéo
[Termes IGN] maille triangulaire
[Termes IGN] modèle de déformation des images
[Termes IGN] niveau de détail
[Termes IGN] noeud
[Termes IGN] optimisation (mathématiques)
[Termes IGN] reconstruction d'objetRésumé : (auteur) This paper presents a novel approach to recover true fine surface detail of deforming meshes reconstructed from multi-view video. Template-based methods for performance capture usually produce a coarse-to-medium scale detail 4D surface reconstruction which does not contain the real high-frequency geometric detail present in the original video footage. Fine scale deformation is often incorporated in a second pass by using stereo constraints, features, or shading-based refinement. In this paper, we propose an alternative solution to this second stage by formulating dense dynamic surface reconstruction as a global optimization problem of the densely deforming surface. Our main contribution is an implicit representation of a deformable mesh that uses a set of Gaussian functions on the surface to represent the initial coarse mesh, and a set of Gaussians for the images to represent the original captured multi-view images. We effectively find the fine scale deformations for all mesh vertices, which maximize photo-temporal-consistency, by densely optimizing our model-to-image consistency energy on all vertex positions. Our formulation yields a smooth closed form energy with implicit occlusion handling and analytic derivatives. Furthermore, it does not require error-prone correspondence finding or discrete sampling of surface displacement values. We demonstrate our approach on a variety of datasets of human subjects wearing loose clothing and performing different motions. We qualitatively and quantitatively demonstrate that our technique successfully reproduces finer detail than the input baseline geometry. Numéro de notice : A2017-401 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007%2Fs11263-016-0979-1 En ligne : https://doi.org/10.1007/s11263-016-0979-1 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85943
in International journal of computer vision > vol 124 n° 1 (August 2017) . - pp 96 – 113[article]Classified and clustered data constellation: An efficient approach of 3D urban data management / Suhaibah Azri in ISPRS Journal of photogrammetry and remote sensing, vol 113 (March 2016)
[article]
Titre : Classified and clustered data constellation: An efficient approach of 3D urban data management Type de document : Article/Communication Auteurs : Suhaibah Azri, Auteur ; Uznir Ujang, Auteur ; Francesc Antón Castro, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 30 - 42 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique
[Termes IGN] analyse de groupement
[Termes IGN] base de données
[Termes IGN] classification dirigée
[Termes IGN] données massives
[Termes IGN] exploration de données
[Termes IGN] gestion urbaine
[Termes IGN] milieu urbain
[Termes IGN] noeud
[Termes IGN] recherche d'information géographiqueRésumé : (auteur) The growth of urban areas has resulted in massive urban datasets and difficulties handling and managing issues related to urban areas. Huge and massive datasets can degrade data retrieval and information analysis performance. In addition, the urban environment is very difficult to manage because it involves various types of data, such as multiple types of zoning themes in the case of urban mixed-use development. Thus, a special technique for efficient handling and management of urban data is necessary. This paper proposes a structure called Classified and Clustered Data Constellation (CCDC) for urban data management. CCDC operates on the basis of two filters: classification and clustering. To boost up the performance of information retrieval, CCDC offers a minimal percentage of overlap among nodes and coverage area to avoid repetitive data entry and multipath query. The results of tests conducted on several urban mixed-use development datasets using CCDC verify that it efficiently retrieves their semantic and spatial information. Further, comparisons conducted between CCDC and existing clustering and data constellation techniques, from the aspect of preservation of minimal overlap and coverage, confirm that the proposed structure is capable of preserving the minimum overlap and coverage area among nodes. Our overall results indicate that CCDC is efficient in handling and managing urban data, especially urban mixed-use development applications. Numéro de notice : A2016-531 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2015.12.008 En ligne : https://doi.org/10.1016/j.isprsjprs.2015.12.008 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81614
in ISPRS Journal of photogrammetry and remote sensing > vol 113 (March 2016) . - pp 30 - 42[article]A wildlife movement approach to optimally locate wildlife crossing structures / Rebecca W. Loraamm in International journal of geographical information science IJGIS, vol 30 n° 1-2 (January - February 2016)PermalinkA hybrid link-node approach for finding shortest paths in road networks with turn restrictions / Qingquan Li in Transactions in GIS, vol 19 n° 6 (December 2015)PermalinkQuerying visible points in large obstructed space / Jianqiu Xu in Geoinformatica, vol 19 n° 3 (July - September 2015)PermalinkA structural-lexical measure of semantic similarity for geo-knowledge graphs / Andrea Ballatore in ISPRS International journal of geo-information, vol 4 n°2 (June 2015)PermalinkA dilution-matching-encoding compaction of trajectories over road networks / Ranit Gotsman in Geoinformatica, vol 19 n° 2 (April - June 2015)PermalinkScale-specific automated line simplification by vertex clustering on a hexagonal tessellation / Paulo Raposo in Cartography and Geographic Information Science, vol 40 n° 5 (November 2013)PermalinkComparison of different strategies for determining raster-based least-cost paths with a minimum amount of distortion / H. Antikainen in Transactions in GIS, vol 17 n° 1 (February 2013)PermalinkVisualisation 3D de terrain texturé : préservation au niveau du pixel des qualités géométriques et colorimétriques, une méthode temps réel, innovante et simple / T.V. Lê in Revue internationale de géomatique, vol 22 n° 3 (septembre - novembre 2012)PermalinkA kernel density estimation method for networks, its computational method and a GIS-based tool / Atsuyuki Okabe in International journal of geographical information science IJGIS, vol 23 n° 1-2 (january 2009)PermalinkVariable-resolution compression of vector data / B. Yang in Geoinformatica, vol 12 n° 3 (September - November 2008)Permalink