Past Government Funded Projects

IMAGIWEB   funded by the French National Research Agency  , with a consortium of 3 labs and 3 companies: analysis of the image life cycle through the Web 2.0

FIRE-ID   This project fits within the general framework of the semantic annotation of visual content that exists in various forms: photos or videos shared on social networks, scanned documents or images captured for video surveillance. This project specifically focuses on the problem of fine-grained analysis and recognition.

DYNAMICITE - The objective of this project is the creation of an overall image of a city by using all available data. The actual situation of the city will be complete as DYNAMICITE uses all traditional and official data about a city but also uses analytics of spontaneous conversations on the web.

CHRONOLINES  This project that addresses the need of creation Event-based Chronologies in a semi-automatic way. Today common manual creation of chronological representations is a time-consuming process. Within Chronolines XRCE will carry out the linguistic analysis of French News Agency (AFP) news articles in both French and English in order to extract temporal information and determine the chronological order of events mentioned in the texts .

COCLICO This project (convergence of the free community for opened collaborative infrastructures) aims at setting up a new dynamic to French software forge communities by giving a framework to this free ecosystem. The project has been labelled by the Minalogic and Systematic Competitiveness Clusters and has obtained subsidies. 

FRAGRANCES  XRCE coordinates this project that will develop an algorithmic for information access in the context of social networks. 

OMNIA  The Omnia project aims at analyzing multimedia documents containing text and images, in a context of data profusion, as they are found on intranets and on Internet. The originality of the project is to work on 3 dimensions (image, text, emotion) and in a multilingual context. Images and texts give rise to 2 categorizations, relative to the informational aspects and to specific emotional aspects (coming directly from the images, or relative to their perception as expressed in the texts). These 2 types of content will be processed independently (annotation followed by indexation and categorization), with learning techniques, and will then be merged at the level of the filter and query tool. Their "primitives" will be linked to an interlingual representation of word senses based on English (UNL), that will open the way to multilingualism at the level of "publishing" the document categories, and of processing queries in natural languages equipped with UNL dictionaries. 

TANGUY This project will develop a system to extract "micro-knowledge" from texts and stock it in a semantic network. 

ALADIN  Smarter document technologies in linguistics that will help control Hospital Acquired Infections (HAIs).

French industrial project supported by the “Agence Nationale de la Recherche (ANR)”. It is a collaboration between the XRCE and INRIA, the French national institute for research in computer science and control. The objective is to design learning algorithms for tree transformations and their implementation for integration of document data (PDF, html, doc) in XML databases. 

INFOMAGIC This project will allow the creation of robust, easy-to-use information extraction and new knowledge consolidation tools in order to increase analysis and collaborative work / decision-making capabilities, dedicated to teachers, competitive watchers, financial analysts, military personnel and researchers. 

For more information contact Florence Helly