Výsledky vyhledávání - "Benoit, Gaüzère"

Symbols Detection and Classification using Graph Neural Networks

Autor: Muhammet Balcilar, Sébastien Adam, Paul Honeine, Pierre Héroux, Benoit Gaüzère, Guillaume Renton

Publikováno v: Pattern Recognition Letters
Pattern Recognition Letters, Elsevier, 2021, ⟨10.1016/j.patrec.2021.09.020⟩

International audience; In this paper, we propose a method to both extract and classify symbols in floorplan images. This method relies on the very recent developments of Graph Neural Networks (GNN). In the proposed approach, floorplan images are fir

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::77895fec2f0d104a1d5ec98f3f5a8f13
https://hal-normandie-univ.archives-ouvertes.fr/hal-03410511

Zobrazit plný text záznamu

Graph kernels based on linear patterns: Theoretical and experimental comparisons

Autor: Paul Honeine, Benoit Gaüzère, Linlin Jia

Publikováno v: Expert Systems with Applications
Expert Systems with Applications, Elsevier, 2021, pp.116095. ⟨10.1016/j.eswa.2021.116095⟩

International audience; Graph kernels are powerful tools to bridge the gap between machine learning and data encoded as graphs. Most graph kernels are based on the decomposition of graphs into a set of patterns. The similarity between two graphs is t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cd821af3266b52a7bde8162b99215a74
https://hal-normandie-univ.archives-ouvertes.fr/hal-03410508

Zobrazit plný text záznamu

A Study on the Stability of Graph Edit Distance Heuristics

Autor: Linlin Jia, Vincent Tognetti, Laurent Joubert, Benoit Gaüzère, Paul Honeine

Publikováno v: Electronics. 11:3312

Graph edit distance (GED) is a powerful tool to model the dissimilarity between graphs. However, evaluating the exact GED is NP-hard. To tackle this problem, estimation methods of GED were introduced, e.g., bipartite and IPFP, during which heuristics

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c2252e745053cc959085a5475480702e
https://doi.org/10.3390/electronics11203312

Zobrazit plný text záznamu

Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective

Autor: Muhammet Balcilar, Renton Guillaume, Pierre Héroux, Benoit Gaüzère, Sébastien Adam, Paul Honeine

Publikováno v: Proceedings of the International Conference on Learning Representations (ICLR)
Proceedings of the International Conference on Learning Representations (ICLR), May 2021, Vienna, Austria
HAL

International audience; In the recent literature of Graph Neural Networks (GNN), the expressive power of models has been studied through their capability to distinguish if two given graphs are isomorphic or not. Since the graph isomorphism problem is

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e745d87ca601e932bcbdcf3e73f9ebbc
https://hal-normandie-univ.archives-ouvertes.fr/hal-03135633

Zobrazit plný text záznamu

graphkit-learn: A Python Library for Graph Kernels Based on Linear Patterns

Autor: Paul Honeine, Benoit Gaüzère, Linlin Jia

Publikováno v: Pattern Recognition Letters
Pattern Recognition Letters, Elsevier, 2021, 143, pp.113-121. ⟨10.1016/j.patrec.2021.01.003⟩

International audience; This paper presents graphkit-learn, the first Python library for efficient computation of graph kernels based on linear patterns, able to address various types of graphs. Graph kernels based on linear patterns are thoroughly i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3083c7f4956516b179f5f1d4794dd9d1
https://hal-normandie-univ.archives-ouvertes.fr/hal-03111016/file/PRL_graphkit_learn__A_Python_Library_for_Graph_Kernels_Based_on_Linear_Patterns.pdf

Zobrazit plný text záznamu

A Metric Learning Approach to Graph Edit Costs for Regression

Autor: Florian Yger, Paul Honeine, Linlin Jia, Benoit Gaüzère

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030739720
S+SSPR
Proceedings of IAPR Joint International Workshops on Statistical techniques in Pattern Recognition (SPR 2020) and Structural and Syntactic Pattern Recognition (SSPR 2020)
Proceedings of IAPR Joint International Workshops on Statistical techniques in Pattern Recognition (SPR 2020) and Structural and Syntactic Pattern Recognition (SSPR 2020), Jan 2021, Venise, Italy
HAL

International audience; Graph edit distance (GED) is a widely used dissimilarity measure between graphs. It is a natural metric for comparing graphs and respects the nature of the underlying space, and provides interpretability for operations on grap

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::032a8cd32398c51d7d9d3cd2b4c3eed4
https://doi.org/10.1007/978-3-030-73973-7_23

Zobrazit plný text záznamu

When Spectral Domain Meets Spatial Domain in Graph Neural Networks

Autor: Muhammet, Balcilar, Guillaume, Renton, Pierre, Héroux, Benoit, Gaüzère, Sébastien, Adam, Honeine, Paul

Publikováno v: Thirty-seventh International Conference on Machine Learning (ICML 2020)-Workshop on Graph Representation Learning and Beyond (GRL+ 2020)
Thirty-seventh International Conference on Machine Learning (ICML 2020)-Workshop on Graph Representation Learning and Beyond (GRL+ 2020), Jul 2020, Vienna, Austria

International audience; Convolutional Graph Neural Networks (Con-vGNNs) are designed either in the spectral domain or in the spatial domain. In this paper, we provide a theoretical framework to analyze these neural networks, by deriving some equivale

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c8e772ee4bb089c1e20f45dcfbe673a9
https://hal-normandie-univ.archives-ouvertes.fr/hal-03088374

Zobrazit plný text záznamu

Graph Neural Network for Symbol Detection on Document Images

Autor: Benoit Gaüzère, Sébastien Adam, Guillaume Renton, Pierre Héroux

Publikováno v: GREC@ICDAR
13th IAPR International Workshop on Graphics Recognition
13th IAPR International Workshop on Graphics Recognition, Sep 2019, Sydney, Australia

International audience; In this paper, we propose a new method to simultaneously detect and classify symbols in floorplan images. This method relies on the very recent developments of Graph Neural Networks (GNN). In the proposed approach, floorplan i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40e11a5b5d59d6e698fc57e51a2e037b
https://doi.org/10.1109/icdarw.2019.00016

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání