Search
Switching et transmission – STAR
Réseaux de communication et récolte d'énergie : optimisation et démonstration – E-CROPS
“Anytime, anywhere, anything” has been the recent catch-phrase used by technology evangelists promising untethered wireless data flow not only among people, but also among devices of any imaginable sort. Trillions of autonomous devices are foreseen in this promise. While wireless sensor networks sol
Évaluation et développement de systèmes d'analyse et de compréhension de textes – Readers
The project proposes new unsupervised computational models to automatically extract background knowledge after reading large amounts of unstructured text. This automatically extracted knowledge is in the form of classes, categorized entities and predicates whose arguments are typified by probability
Annotation de données visuelles avec des descriptions sémantiques – ViSen
Today a typical Web document will contain a mix of visual and textual content. Most traditional tools for search and retrieval can successfully handle textual content, but are not prepared to handle hetereogeneous documents. The new type of content demands the development of new efficient tools f
Architecture multifonctionnelle et technologie pour capteur sans fil intelligent autonome en énergie – SMARTER
"The overall vision of the project is to develop comprehensive knowledge and an innovative methodology in the areas of energy autonomous wireless systems from a global system perspective, enabling self-powered, battery-free wireless sensing nodes to meet a wide range of structural health monitoring
Extraction de Connaissances et Crédibilité Utilisateurs pour le Multimédiz – MUCKE
Web3.0 has already appeared in the public vocabulary over 5 years ago. While its definition remains unclear, what has become clear in the last half decade is that the web has become a support for social media. Directly from cameras, phones, tablets or computers, users are pushing multimedia data tow
Annotation collaborative de documents multi-modaux, multi-lingues et multi-média – CAMOMILE
Human activity is constantly generating large volumes of heterogeneous data, in particular via the Web. These data can be collected and explored to gain new insights in social sciences, linguistics, economics, behavioural studies as well as artificial intelligence and computer sciences. In this reg
Repenser l'essence, la flexibilité et la réutilisabilité de l'exploitation de modèles avancés – REFRAME
Reuse of learnt knowledge is of critical importance in the majority of knowledge-intensive application areas, particularly because the operating context can be expected to vary from training to deployment. In machine learning this is most commonly studied in relation to variations in class and cost
Calculateurs humains pour l'extraction de connaissance et l'évaluation – uComp
The rapid growth and fragmented character of social media and publicly available structured data challenges established approaches to knowledge extraction. Many algorithms fail when they encounter noisy, multilingual and contradictory input. Efforts to increase the reliability and scalability of the