We describe a new information fusion approach to integrate facts extracted from cross-media objects (videos and texts)into a coherent common represen- tation including multi-level knowledge (concepts,relations and events).Beyond standard information fusion,we ex- ploited video extraction results and sig- nificantly improved text Information Ex- traction.We further extended our meth- ods to multi-lingual environment (Eng- lish,Arabic and Chinese)by presenting a case study on cross-lingual comparable corpora acquisition based on video com- parison.
展开▼