{"type":"ScholarlyArticle","title":"General Purpose Models: Expectations About The Unexpected","authors":[{"name":"Steven W. Zucker","slug":"steven-w-zucker","given":"Steven W.","family":"Zucker","affiliation":""},{"name":"Azriel Rosenfeld","slug":"azriel-rosenfeld","given":"Azriel","family":"Rosenfeld","affiliation":""},{"name":"Larry S. Davis","slug":"larry-s-davis","given":"Larry S.","family":"Davis","affiliation":""}],"abstract":"How can computer vision systems be designed to handle unfamiliar or unexpected sc~nes? Many of the current systems cope qu~te well with limited visual worlds, by mak~ng use of specialized knowledge about these worlds. But if we want to expand t~ese systems to handle a wide range of v7sual domains, it will not be enough to s~mply employ a large number of specialized models. It will also be important to make use of what might be called \"general-purpose models.\" Such models can be used to suggest reasonable descriptions for a given scene, e.g., in terms of ~eatures or regions or groups of these, ~n the absence of specific context.","doi":null,"url":"https://ijcai.org/proceedings/1975/113","pdf":"https://ijcai.org/proceedings/1975/0113.pdf","markdown":"https://ijcai.org/proceedings/1975/113.md","bibtex":"https://ijcai.org/proceedings/1975/bibtex/113","volume":{"slug":"1975","title":"Proceedings of the Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1975","url":"https://ijcai.org/proceedings/1975/","year":1975,"location":"Tbilisi, Georgia, USSR","dates":"","editors":"Patrick Winston and Carl Hewitt","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Visual Information Processing","track":"Visual Information Processing","number":113,"pages":{"first":716,"last":720},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}