Please use this identifier to cite or link to this item:
http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6659Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.creator | Miller, Erik G. | - |
| dc.creator | Tieu, Kinh | - |
| dc.creator | Stauffer, Chris P. | - |
| dc.date | 2004-10-08T20:36:37Z | - |
| dc.date | 2004-10-08T20:36:37Z | - |
| dc.date | 2001-09-01 | - |
| dc.date.accessioned | 2013-10-09T02:46:23Z | - |
| dc.date.available | 2013-10-09T02:46:23Z | - |
| dc.date.issued | 2013-10-09 | - |
| dc.identifier | AIM-2001-021 | - |
| dc.identifier | http://hdl.handle.net/1721.1/6659 | - |
| dc.identifier.uri | http://koha.mediu.edu.my:8181/xmlui/handle/1721 | - |
| dc.description | We 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. | - |
| dc.format | 9 p. | - |
| dc.format | 8233900 bytes | - |
| dc.format | 814636 bytes | - |
| dc.format | application/postscript | - |
| dc.format | application/pdf | - |
| dc.language | en_US | - |
| dc.relation | AIM-2001-021 | - |
| dc.subject | AI | - |
| dc.subject | Invariance | - |
| dc.subject | Optical Flow | - |
| dc.subject | Color Constancy | - |
| dc.subject | Object Recognition | - |
| dc.subject | image manifold | - |
| dc.title | Learning Object-Independent Modes of Variation with Feature Flow Fields | - |
| Appears in Collections: | MIT Items | |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.