Show simple item record

Contextual Priming for Object Detection

dc.date.accessioned2004-10-20T21:03:49Z
dc.date.accessioned2018-11-24T10:23:28Z
dc.date.available2004-10-20T21:03:49Z
dc.date.available2018-11-24T10:23:28Z
dc.date.issued2001-09-01en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/7239
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/7239
dc.description.abstractThere is general consensus that context can be a rich source of information about an object's identity, location and scale. In fact, the structure of many real-world scenes is governed by strong configurational rules akin to those that apply to a single object. Here we introduce a simple probabilistic framework for modeling the relationship between context and object properties based on the correlation between the statistics of low-level features across the entire scene and the objects that it contains. The resulting scheme serves as an effective procedure for object priming, context driven focus of attention and automatic scale-selection on real-world scenes.en_US
dc.format.extent27 p.en_US
dc.format.extent40187890 bytes
dc.format.extent5238575 bytes
dc.language.isoen_US
dc.subjectAIen_US
dc.subjectcontexten_US
dc.subjectimage statisticsen_US
dc.subjectBayesian reasoningen_US
dc.subjectrecognitionen_US
dc.subjectfocus of attentionen_US
dc.titleContextual Priming for Object Detectionen_US


Files in this item

FilesSizeFormatView
AIM-2001-020.pdf5.238Mbapplication/pdfView/Open
AIM-2001-020.ps40.18Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record