Although there has been much progress in developing theories, models and systems in the areas of Natural Language Processing (NLP) and Vision Processing (VP) there has been little progress on integrating these sub-areas of Artificial Intelligence (AI). This book contains a set of edited papers addressing computational models and systems for the integration of NLP and VP. The papers focus on site descriptions such as that of the large Japanese $500 million Real World Computing (RWC) project, on historical philosophical issues, on systems which have been built and which integrate the processing of visual scenes together with language about them, and on spatial relations which appear to be the key to integration. The USA, Japan and the EU are well reflected in the study.