. German Research Center for Artificial Intelligence GmbH
The project VITRA (VIsual TRAnslator) deals with the relationship between natural language and vision. Experimental studies are being carried out in the way of designing an interface between image understanding and natural language systems, with the aim of developing systems for the natural language description of image sequences. During the last ten years several domains of application have been investigated and an approach for integrating language and vision has evolved, which allows incremental evaluation and simultaneous natural language description of real world image sequences. This contribution provides a compact description of the VITRA conception and presents some of the results obtained so far. Current limitations of the approach and future research tasks will be discussed as well.