Personalised AdveRtisements built from web Sources

Start date
May 1, 2012
End date
April 30, 2016
KU Leuven LIIR (Sien Moens, Coordinator); KU Leuven ESAT-Visics (Luc Van Gool, Tinne Tuytelaars), KU Leuven HCI (Erik Duval), Ghent University - CWI (Martine De Cock), VLERICK (Steve Muylle), UA (Patrick Van Eecke)
Research portal


User generated content, e.g. available through social networking sites on the Web, offers a wealth of information. The aim of PARIS is to study adequate natural language, image and video understanding techniques to make use of this information. This is challenging as user generated content is often present in language that is not well-formed or in visual material that is not professionally captured. An important application of PARIS to evaluate the natural language, image and video understanding techniques is personalised advertising, where advertisements are searched and generated that fit the world of living of users. This personalisation should remain in line with legal requirements concerning personal data protection and intellectual property rights.