IMAGINE ¿ Cross-modal information extraction for improved image meta data

• Unité de recherche: INNOSUISSE
• Numéro de projet: 17853.1 PFES-ES
• Titre du projet anglais: IMAGINE ¿ Cross-modal information extraction for improved image meta data

Description succincte (Allemand)

IMAGINE ¿ Cross-modal information extraction for improved image meta data

Description succincte (Anglais)

IMAGINE ¿ Cross-modal information extraction for improved image meta data

Résumé des résultats (Abstract) (Allemand)

The retrieval and marketability of visual content highly depends on the availability of high quality image meta data which enables customers to efficiently locate relevant content in large image collections.|The IMAGINE project develops advanced information extraction methods which exploit the convergence between textual image descriptions and image content as well as linked open data to automatically obtain relevant meta data such as keywords, named entities and topics.

Résumé des résultats (Abstract) (Anglais)