Contextual Priming for Object Detection

dc.creator	Torralba, Antonio
dc.creator	Sinha, Pawan
dc.date	2004-10-20T21:03:49Z
dc.date	2004-10-20T21:03:49Z
dc.date	2001-09-01
dc.date.accessioned	2013-10-09T02:48:38Z
dc.date.available	2013-10-09T02:48:38Z
dc.date.issued	2013-10-09
dc.identifier	AIM-2001-020
dc.identifier	CBCL-205
dc.identifier	http://hdl.handle.net/1721.1/7239
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	There 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.
dc.format	27 p.
dc.format	40187890 bytes
dc.format	5238575 bytes
dc.format	application/postscript
dc.format	application/pdf
dc.language	en_US
dc.relation	AIM-2001-020
dc.relation	CBCL-205
dc.subject	AI
dc.subject	context
dc.subject	image statistics
dc.subject	Bayesian reasoning
dc.subject	recognition
dc.subject	focus of attention
dc.title	Contextual Priming for Object Detection

Files in this item

Files	Size	Format	View
There are no files associated with this item.