"People are now more connected than ever before thanks to the technological advances of personal computers, smart personal devices, as well as global Internet connections. Web-based services like Flickr and YouTube and social networks such as Facebook have become more and more popular, allowing people to easily upload, share and annotate personal media content. This connectivity constitutes a new key source of information.
In this project, the candidate will focus on the problem of exploiting semantic and social knowledge for visual recognition. In fact, although visual data are the largest component of the digital world, they have been so far excluded from most social media research.
Some recent works have begun to take social network analysis into account when looking at visual data, but their scope has been too limited. Researchers have presented algorithms for enriching user annotations through tag recommendation strategies (often focusing only on tags and their relations), and methods for estimating tag relevance in order to rank and filter the list of tags. Nevertheless, most of these studies were conducted in simplified settings and do not address the full information given by visual media and their social and semantic relations.
This project goes beyond these studies by introducing a new framework which jointly models objective knowledge, given by the visual appearance, prior knowledge, given by visual and linguistic ontologies, and noisy collective knowledge, given by social tags and social relations. This is a challenging issue since, at the scale of web, we are looking at connections of thousands of elements. Experiments will be conducted on a large-scale image benchmark.
The contribution to EU scientific and technological knowledge and researcher training will be enhanced by taking advantage of the extensive experience and outcomes attained by the third-country organization (Stanford University) in the field of high-level visual recognition."
Call for proposal
See other projects for this call