Show simple item record

Learning Object-Independent Modes of Variation with Feature Flow Fields

dc.date.accessioned2004-10-08T20:36:37Z
dc.date.accessioned2018-11-24T10:21:25Z
dc.date.available2004-10-08T20:36:37Z
dc.date.available2018-11-24T10:21:25Z
dc.date.issued2001-09-01en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/6659
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/6659
dc.description.abstractWe present a unifying framework in which "object-independent" modes of variation are learned from continuous-time data such as video sequences. These modes of variation can be used as "generators" to produce a manifold of images of a new object from a single example of that object. We develop the framework in the context of a well-known example: analyzing the modes of spatial deformations of a scene under camera movement. Our method learns a close approximation to the standard affine deformations that are expected from the geometry of the situation, and does so in a completely unsupervised (i.e. ignorant of the geometry of the situation) fashion. We stress that it is learning a "parameterization", not just the parameter values, of the data. We then demonstrate how we have used the same framework to derive a novel data-driven model of joint color change in images due to common lighting variations. The model is superior to previous models of color change in describing non-linear color changes due to lighting.en_US
dc.format.extent9 p.en_US
dc.format.extent8233900 bytes
dc.format.extent814636 bytes
dc.language.isoen_US
dc.subjectAIen_US
dc.subjectInvarianceen_US
dc.subjectOptical Flowen_US
dc.subjectColor Constancyen_US
dc.subjectObject Recognitionen_US
dc.subjectimage manifolden_US
dc.titleLearning Object-Independent Modes of Variation with Feature Flow Fieldsen_US


Files in this item

FilesSizeFormatView
AIM-2001-021.pdf814.6Kbapplication/pdfView/Open
AIM-2001-021.ps8.233Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record