Centre dedocumentation
scientifique

Challenging deep image descriptors for retrieval in heterogeneous iconographic collections / Dimitri Gominski (2019)  

Public contenu dans ArXiv / Université Cornell (Etats-Unis) (1991)   Titre : Challenging deep image descriptors for retrieval in heterogeneous iconographic collections Type de document : Article/Communication Auteurs : Dimitri Gominski, Auteur ; Martyna Poreba , Auteur ; Valérie Gouet-Brunet , Auteur ; Liming Chen, Auteur Congrès : SUMAC 2019, 1st workshop on Structuring and Understanding of Multimedia heritAge Contents (21 octobre 2019; Nice, France) , Commanditaire Editeur : New York [Etats-Unis] : Association for computing machinery ACM Année de publication : 2019 Autre Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Importance : pp 31 - 38 Format : 21 x 30 cm Note générale : bibliographie Preprint publié sur ArXiv Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] analyse visuelle [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] base de données d'images [Termes descripteurs IGN] collection [Termes descripteurs IGN] descripteur [Termes descripteurs IGN] données hétérogènes [Termes descripteurs IGN] exploration de données [Termes descripteurs IGN] extraction de traits caractéristiques [Termes descripteurs IGN] iconographie [Termes descripteurs IGN] image multi sources [Termes descripteurs IGN] indexation [Termes descripteurs IGN] jeu de données [Termes descripteurs IGN] recherche d'image basée sur le contenu Résumé : (auteur) This article proposes to study the behavior of recent and efficient state-of-the-art deep-learning based image descriptors for content-based image retrieval, facing a panel of complex variations appearing in heterogeneous image datasets, in particular in cultural collections that may involve multi-source, multi-date and multi-view contents. For this purpose, we introduce a novel dataset, namely Alegoria dataset, consisting of 12,952 iconographic contents representing landscapes of the French territory, and encapsultating a large range of intra-class variations of appearance which were finely labelled. Six deep features (DELF, NetVLAD, GeM, MAC, RMAC, SPoC) and a hand-crafted local descriptor (ORB) are evaluated against these variations. Their performance are discussed, with the objective of providing the reader with research directions for improving image description techniques dedicated to complex heterogeneous datasets that are now increasingly present in topical applications targeting heritage valorization. Numéro de notice : C2019-022 Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1145/3347317.3357246 date de publication en ligne : 19/09/2019 En ligne : https://doi.org/10.1145/3347317.3357246 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93623

Voir aussi

• SUMAC 2019, 1st workshop on Structuring and Understanding of Multimedia heritAge Contents / Valérie Gouet-Brunet (2019)  

SUMAC 2019, 1st workshop on Structuring and Understanding of Multimedia heritAge Contents / Valérie Gouet-Brunet (2019)  

Public Titre : SUMAC 2019, 1st workshop on Structuring and Understanding of Multimedia heritAge Contents Type de document : Article/Communication Auteurs : Valérie Gouet-Brunet , Editeur scientifique ; Margarita Khokhlova, Editeur scientifique ; Liming Chen, Editeur scientifique ; Sander Münster, Editeur scientifique ; Sander Münster Congrès : MM 2019, 27th ACM International Conference on Multimedia (21 - 25 octobre 2019; Nice, France), Auteur Editeur : New York [Etats-Unis] : Association for computing machinery ACM Année de publication : 2019 Importance : pp 2726 - 2727 Format : 21 x 30 cm Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] données massives [Termes descripteurs IGN] patrimoine culturel [Termes descripteurs IGN] patrimoine immobilier [Termes descripteurs IGN] recherche scientifique [Termes descripteurs IGN] valorisation Résumé : (auteur) SUMAC 2019 is the first workshop on Structuring and Understanding of Multimedia heritAge Contents. It is held in Nice, France on October 21, 2019 and is co-located with the 27th ACM International Conference on Multimedia. Its objective is to present and discuss the latest and most significant trends and challenges in the analysis, structuring and understanding of multimedia contents dedicated to the valorization of heritage, with the emphasis on the unlocking of and access to the big data of the past. A representative scope of Computer Science methodologies dedicated to the processing of multimedia heritage contents and their exploitation is covered by the works presented, with the ambition of advancing and raising awareness about this fully developing research field. Numéro de notice : 25324 Thématique : GEOMATIQUE/IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1145/3343031.3350554 En ligne : https://doi.org/10.1145/3343031.3350554 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93622

Voir aussi

• Challenging deep image descriptors for retrieval in heterogeneous iconographic collections / Dimitri Gominski (2019)  

Assessing the planimetric accuracy of Paris atlases from the late 18th and 19th centuries / Bertrand Duménieu (2018)    

Public Titre : Assessing the planimetric accuracy of Paris atlases from the late 18th and 19th centuries Type de document : Article/Communication Auteurs : Bertrand Duménieu , Auteur ; Nathalie Abadie , Auteur ; Julien Perret , Auteur Congrès : SAC 2018, 33rd Annual ACM Symposium on Applied Computing (9 - 13 avril 2018; Pau, France) , Commanditaire ; Congrès: KEGeod 2018, Knowledge Extraction from Geographical Data Technical tracks of SAC 2018 (9 - 13 avril 2018; Pau, France), Commanditaire Editeur : New York [Etats-Unis] : Association for computing machinery ACM Année de publication : 2018 Projets : 1-Pas de projet / Importance : pp 876 - 883 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes descripteurs IGN] carte ancienne [Termes descripteurs IGN] dix-huitième siècle [Termes descripteurs IGN] dix-neuvième siècle [Termes descripteurs IGN] géoréférencement [Termes descripteurs IGN] géoréférencement indirect [Termes descripteurs IGN] Paris (75) [Termes descripteurs IGN] point d'appui [Termes descripteurs IGN] précision planimétrique [Termes descripteurs IGN] projection Résumé : (auteur) The recent initiatives to digitize cultural heritage resources and publish them on the Web have renewed interest in historical maps for the diachronic analysis of territories in GIS applications. However, such analyses should not be done without a good understanding of the possibilities and limitations of geographical information provided by historical maps, i.e. their quality. One of the major concerns regarding historical maps quality is their positional planimetric accuracy which highly depends on survey techniques used at the time. As these techniques are not always thoroughly known and as ground truth is most of the time not sufficiently available, direct absolute evaluation approaches have been proposed to assess historical maps positional planimetric accuracy. In this article, we follow the intuition that the most widely adopted georeferencing-based approach for assessing the positional planimetric accuracy of historical maps can be adapted to provide an evaluation of the error caused by the survey process in cases like Paris atlases where the georeferencing transformation can be estimated with ground control points based on geodetic features and where the projection of the map can be approximated by a well known projected coordinate reference system. We apply this tuned approach on the Verniquet atlas and evaluate the validity of our hypothesis about projection approximation. Numéro de notice : C2018-019 Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1145/3167132.3167228 date de publication en ligne : 15/04/2018 En ligne : https://doi.org/10.1145/3167132.3167228 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90481

Documents numériques

en open access Assessing the planimetric accuracy of Paris atlases ... - postprint Adobe Acrobat PDF

An adaptive approach for interlinking georeferenced data / Abdelfettah Feliachi (2017)  

Public Titre : An adaptive approach for interlinking georeferenced data Type de document : Article/Communication Auteurs : Abdelfettah Feliachi, Auteur ; Nathalie Abadie , Auteur ; Fayçal Hamdi, Auteur Congrès : K-CAP 2017, 9th international conference on knowledge capture (4 - 6 décembre 2017; Austin, Texas - Etats-Unis), Commanditaire Editeur : New York [Etats-Unis] : Association for computing machinery ACM Année de publication : 2017 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes descripteurs IGN] incertitude des données [Termes descripteurs IGN] modèle géométrique [Termes descripteurs IGN] précision de localisation [Termes descripteurs IGN] qualité des données [Termes descripteurs IGN] Web des données Résumé : (auteur) The resources published on the Web of data are often described by spatial references such as coordinates. The common data linking approaches are mainly based on the hypothesis that spatially close resources are more likely to represent the same thing. However, this assumption is valid only when the spatial references that are compared have been produced with the same positional accuracy, and when they actually represent the same spatial characteristic of the resources captured in an unambiguous way. Otherwise, spatial distance-based matching algorithms may produce erroneous links. In this article, we first suggest to formalize and acquire the knowledge about the spatial references, namely their positional accuracy, their geometric modeling, their level of detail, and the vagueness of the spatial entities they represent. We then propose an interlinking approach that dynamically adapts the way spatial references are compared, based on this knowledge. Numéro de notice : C2017-024 Thématique : GEOMATIQUE/INFORMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1145/3148011.3148025 date de publication en ligne : 20/12/2017 En ligne : https://doi.org/10.1145/3148011.3148025 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89286

Continuously generalizing buildings to built-up areas by aggregating and growing / Dongliang Peng (2017)  

Public Titre : Continuously generalizing buildings to built-up areas by aggregating and growing Type de document : Article/Communication Auteurs : Dongliang Peng, Auteur ; Guillaume Touya , Auteur Congrès : UrbanGIS 2017, 3rd ACM SIGSPATIAL workshop (7 - 10 novembre 2017; Redondo Beach, Californie - Etats-Unis), Commanditaire Editeur : New York [Etats-Unis] : Association for computing machinery ACM Année de publication : 2017 Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] bati [Termes descripteurs IGN] construction [Termes descripteurs IGN] distance euclidienne [Termes descripteurs IGN] mise à l'échelle [Termes descripteurs IGN] polygone [Termes descripteurs IGN] simplification de contour [Vedettes matières IGN] Généralisation Résumé : (auteur) To enable smooth zooming, we propose a method to continuously generalize buildings from a given start map to a smaller-scale goal map, where there are only built-up area polygons instead of individual building polygons. We name the buildings on the start map original buildings. For an intermediate scale, we aggregate the original buildings that will become too close by adding bridges. We grow (bridged) original buildings based on buffering, and simplify the grown buildings. We take into account the shapes of the buildings both at the previous map and goal map to make sure that the buildings are always growing. The running time of our method is in O (n3), where n is the number of edges of all the original buildings. The advantages of our method are as follows. First, the buildings grow continuously and, at the same time, are simplified. Second, right angles of buildings are preserved during growing: the merged buildings still look like buildings. Third, the distances between buildings are always larger than a specified threshold. We do a case study to show the performances of our method. Numéro de notice : C2017-027 Thématique : GEOMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1145/3152178.3152188 date de publication en ligne : 01/12/2017 En ligne : https://doi.org/10.1145/3152178.3152188 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89290

Evaluation of NER systems for the recognition of place mentions in French thematic corpora / Carmen Brando (2016)  

Permalink

Progressive streaming and massive rendering of 3D city models on web-based virtual globe / Quoc Dinh Nguyen (2016)  

Permalink

Realtime projective multi-texturing of pointclouds and meshes for a realistic street-view web navigation / Alexandre Devaux (2016)    

Permalink

A multi-layer markup language for geospatial semantic annotations / Ludovic Moncla (2015)  

Permalink

Proceedings of the 9th Workshop on Geographic Information Retrieval, GIR'2015 / Ross S. Purves (2015)  

Permalink

TEXTOMAP : determining geographical window for texts / Geoffrey Brun (2015)  

Permalink

2D arrangement-based hierarchical spatial partitioning: an application to pedestrian network generation / Murat Yirci (2013)  

Permalink

A 3D geospatial registration service for street level co-visualization of 2D vector maps / Quoc Dinh Nguyen (2013)  

Permalink

Accentuating focus maps via partial schematization / Thomas van Dijk (2013) 

Permalink

Extracting semantics of individual places from movement data by analyzing temporal patterns of visits / Gennady Andrienko (2013)    

Permalink