Show simple item record

dc.contributor.authorRowe, Neil C.
dc.dateJuly 1998
dc.date.accessioned2013-09-20T16:11:15Z
dc.date.available2013-09-20T16:11:15Z
dc.date.issued1998-07
dc.identifier.urihttp://hdl.handle.net/10945/36566
dc.descriptionThis paper appeared in the AAAI-98 Workshop on Representations for Multi-Modal Human-Computer Interaction, July 1998, Madison, Wisconsin, USA.en_US
dc.description.abstractWe discuss the obstacles to inference of correspondances between objects within photographic images and their counterpart concepts in descriptive captions of those images. This is important for information retrieval of photographic data since its content analysis is much harder than linguistic analysis of its captions. We argue that the key mapping is between certain caption concepts representing the "linguistic focus" and certain image regions representing the "visual focus". The mapping is one-to-many, however, and many image regions and captions concepts are not mapped at all. We discuss some domain-independent constraints that can restrict potential mappings. We also report on experiments testing our criteria for visual focus of images.en_US
dc.description.sponsorshipsupported by the U.S. Army Artificial Intelligence Center, and by the U. S. Naval Postgraduate Schoolen_US
dc.publisherMonterey, California. Naval Postgraduate Schoolen_US
dc.titleMapping between image regions and caption concepts of captioned depictive photographsen_US
dc.typeConference Paperen_US
dc.description.funderfunds provided by the Chief for Naval Operationsen_US
dc.description.distributionstatementApproved for public release; distribution is unlimited.


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record