BIASED MANIFOLD LEARNING FOR VIEW INVARIANT BODY POSE ESTIMATION
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hur, Dongcheol | - |
dc.contributor.author | Suk, Heung-Il | - |
dc.contributor.author | Wallraven, Christian | - |
dc.contributor.author | Lee, Seong-Whan | - |
dc.date.accessioned | 2021-09-06T13:46:27Z | - |
dc.date.available | 2021-09-06T13:46:27Z | - |
dc.date.created | 2021-06-15 | - |
dc.date.issued | 2012-11 | - |
dc.identifier.issn | 0219-6913 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/107050 | - |
dc.description.abstract | In human body pose estimation, manifold learning has been considered as a useful method with regard to reducing the dimension of 2D images and 3D body configuration data. Most commonly, body pose is estimated from silhouettes derived from images or image sequences. A major problem in applying manifold estimation to pose estimation is its vulnerability to silhouette variation caused by changes of factors such as viewpoint, person, and distance. In this paper, we propose a novel approach that combines three separate manifolds for viewpoint, pose, and 3D body configuration focusing on the problem of viewpoint-induced silhouette variation. The biased manifold learning is used to learn these manifolds with appropriately weighted distances. The proposed method requires four mapping functions that are learned by a generalized regression neural network for robustness. Despite the use of only three manifolds, experimental results show that the proposed method can reliably estimate 3D body poses from 2D images with all learned viewpoints. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | WORLD SCIENTIFIC PUBL CO PTE LTD | - |
dc.subject | REGRESSION | - |
dc.title | BIASED MANIFOLD LEARNING FOR VIEW INVARIANT BODY POSE ESTIMATION | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Suk, Heung-Il | - |
dc.contributor.affiliatedAuthor | Wallraven, Christian | - |
dc.contributor.affiliatedAuthor | Lee, Seong-Whan | - |
dc.identifier.doi | 10.1142/S0219691312500580 | - |
dc.identifier.scopusid | 2-s2.0-84871588370 | - |
dc.identifier.wosid | 000314539000008 | - |
dc.identifier.bibliographicCitation | INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING, v.10, no.6 | - |
dc.relation.isPartOf | INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING | - |
dc.citation.title | INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING | - |
dc.citation.volume | 10 | - |
dc.citation.number | 6 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Mathematics | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Software Engineering | - |
dc.relation.journalWebOfScienceCategory | Mathematics, Interdisciplinary Applications | - |
dc.subject.keywordPlus | REGRESSION | - |
dc.subject.keywordAuthor | 3D pose estimation | - |
dc.subject.keywordAuthor | manifold learning | - |
dc.subject.keywordAuthor | nonlinear dimensionality reduction | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.