Homeomorphic Manifold Analysis (HMA): Generalized separation of style and content on manifolds

Title
Homeomorphic Manifold Analysis (HMA): Generalized separation of style and content on manifolds
Author(s)
이찬수Ahmed Elgammal[Ahmed Elgammal]
Keywords
DIMENSIONALITY REDUCTION; APPEARANCE; TRACKING; MODELS; REPRESENTATION; APPROXIMATION; RECOGNITION; PEOPLE; SHAPE
Issue Date
201304
Publisher
ELSEVIER SCIENCE BV
Citation
IMAGE AND VISION COMPUTING, v.31, no.4, pp.291 - 310
Abstract
The problem of separation of style and content is an essential element of visual perception, and is a fundamental mystery of perception. This problem appears extensively in different computer vision applications. The problem we address in this paper is the separation of style and content when the content lies on a low-dimensional nonlinear manifold representing a dynamic object. We show that such a setting appears in many human motion analysis problems. We introduce a framework for learning parameterization of style and content in such settings. Given a set of topologically equivalent manifolds, the Homeomorphic Manifold Analysis (HMA) framework models the variation in their geometries in the space of functions that maps between a topologically-equivalent common representation and each of them. The framework is based on decomposing the style parameters in the space of nonlinear functions that map between a unified embedded representation of the content manifold and style-dependent visual observations. We show the application of the framework in synthesis, recognition, and tracking of certain human motions that follow this setting, such as gait and facial expressions. (C) 2012 Published by Elsevier B.V.
URI
http://hdl.handle.net/YU.REPOSITORY/26024http://dx.doi.org/10.1016/j.imavis.2012.12.003
ISSN
0262-8856
Appears in Collections:
공과대학 > 전자공학과 > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE