Search results for "Semantic"
showing 10 items of 941 documents
Incorporating depth information into few-shot semantic segmentation
2021
International audience; Few-shot segmentation presents a significant challengefor semantic scene understanding under limited supervision.Namely, this task targets at generalizing the segmentationability of the model to new categories given a few samples.In order to obtain complete scene information, we extend theRGB-centric methods to take advantage of complementary depthinformation. In this paper, we propose a two-stream deep neuralnetwork based on metric learning. Our method, known as RDNet,learns class-specific prototype representations within RGB anddepth embedding spaces, respectively. The learned prototypesprovide effective semantic guidance on the corresponding RGBand depth query ima…
Semantic User Profiling for Digital Advertising
2015
International audience; With the emergence of real-time distribution of online advertising space (“real-time bidding”), user profiling from web navigation traces becomes crucial. Indeed, it allows online advertisers to target customers without interfering with their activities. Current techniques apply traditional methods as statistics and machine learning, but suffer from their limitations. As an answer, the proposed approach aims to develop and evaluate a semantic-based user profiling system for digital advertising.
TOWARDS SEMANTIC INTEROPERABILITY FOR ENTERPRISE INFORMATION SYSTEMS
2016
International audience; In the context of globalisation, data and knowledge management, and given the need to deliver a quick response to changes in market forces, enterprises have to collaborate using information technologies to succeed in a disparate and dynamical business environment. Enterprise interoperability (EI) is a field of study that aims to improve this collaboration. Moreover, EI addresses problems related to the lack of system interoperability in organisations. In this paper, we focus on approaches which deliver semantic interoperability among enterprise information systems. We conclude by identifying the main drawbacks of such approaches to be adopted by world-wide industry a…
FOWLA, A Federated Architecture for Ontologies.
2015
International audience; The progress of information and communication technologies has greatly increased the quantity of data to process. Thus, managing data heterogeneity is a problem nowadays. In the 1980s, the concept of a Federated Database Architecture (FDBA) was introduced as a collection of components to unite loosely coupled federation. Semantic web technologies mitigate the data heterogeneity problem, however due to the data structure heterogeneity the integration of several ontologies is still a complex task. For tackling this problem, we propose a loosely coupled federated ontology architecture (FOWLA). Our approach allows the coexistence of various ontologies sharing common data…
Enhancing scientific information systems with semantic annotations
2013
International audience; Scientific Information Systems aim to produce or improve knowledge on a subject through activities of research and development. The management of scientific dat a requires some essential properties. We propose SemLab an architecture that sup ports interoperability, data quality and extensibility through a unique paradigm: semantic annotation. We present two app lications that validate our architecture.
How to Enrich Description Logics with Fuzziness
2017
International audience; The paper describes the relation between fuzzy and non-fuzzy description logics. It gives an overview about current research in these areas and describes the difference between tasks for description logics and fuzzy logics. The paper also deals with the transformation properties of description logics to fuzzy logics and backwards. While the process of transformation from a description logic to a fuzzy logic is a trivial inclusion, the other way of reducing information from fuzzy logic to description logic is a difficult task, that will be topic of future work.
Customizing Semantic Profiling for Digital Advertising
2014
International audience; Personalization is the new magic buzzword of application development. To make the complexity of today's application functionalities and information spaces "digestible", customization has become the new go-to technique. But while those technologies aim to ease the consumption of media for their users, they suffer from the same problematic: in the age of Big Data, applications have to cope with a conundrum of heterogeneous information sources that have to be perceived, processed and interpreted. Researchers tend to aim for a maximum degree of integration to create the perfect, all-embracing personalization. The results are wide-range, but overly complex systems that su…
Multi-Domain Retrieval of Geospatial Data Sources Implementing a Semantic Catalogue
2015
International audience; Nowadays, the expertise of a user plays an important role in the search and retrieval in the information systems that usually combines general and specialized knowledge in the construction of queries. In addition, most of the queries systems are currently restricted on specific domains. Tackling these issues, we propose a methodology that implements a semantic catalogue in order to provide a smart queries system for retrieving data sources on the web by means of the extension of the user expertise. We propose the combination of a query expansion method, and the use of similarity measures and controlled vocabularies. Thus, it allows the system to recommend data source…
Integration of Spatial Technologies and Semantic Web Technologies for Industrial Archaeology
2010
International audience; We propose a method that uses the advancement in spatial technologies from current database systems within the Semantic Web Technologies in order to enrich and to populate the knowledge of a domain defined in an OWL-DL ontology. The results of spatial operations and functions are used to populate and to enrich ontologies with new individuals and new relationships. The advantage of spatial analysis within Semantic Web technologies is the diversity of the functionalities provided by the combination of spatial operations and the rule language of the Semantic Web (SWRL). This method is applied in the industrial archaeology domain in order to enhance the knowledge managem…
Graphe-Based Rules For XML Data Conversion to OWL Ontology
2010
International audience; The paper presents a flexible method to enrich and populate an existing OWL ontology from XML data based on graph-based rules. These rules are defined in order to populate automatically a new version of an OWL ontology. Today, most of data exchanged between information systems is done with the help of the XML document. Leading researches in the domain of database systems are moving to semantic model in order to store data and its semantics definition. This flexible method consists in populating an existing OWL ontology from XML data. In paper we present such a method based on the definition of a graph which represents rules that drive the populating process.