Implicit Semantic Data Augmentation for Hand Pose Estimation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Seo, Kyeongeun | - |
dc.contributor.author | Cho, Hyeonjoong | - |
dc.contributor.author | Choi, Daewoong | - |
dc.contributor.author | Park, Ju-Derk | - |
dc.date.accessioned | 2022-09-25T10:40:32Z | - |
dc.date.available | 2022-09-25T10:40:32Z | - |
dc.date.created | 2022-09-23 | - |
dc.date.issued | 2022 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/143994 | - |
dc.description.abstract | Data augmentation is a well-known technique used for improving the generalization performance of modern neural networks. After the success of several traditional random data augmentation for images (including flipping, translation, or rotation), a recent surge of interest in implicit data augmentation techniques occurs to complement random data augmentation techniques. Implicit data augmentation augments training samples in feature space, rather than in pixel space, resulting in the generation of semantically meaningful data. Several techniques on implicit data augmentation have been introduced for classification tasks. However, few approaches have been introduced for regression tasks with continuous/structured labels, such as object pose estimation. Hence, we are motivated to propose a method for implicit semantic data augmentation for hand pose estimation. By considering semantic distances of hand poses, the proposed method implicitly generates extra training samples in feature space. We propose two additional techniques to improve the performance of this augmentation: metric learning and hand-dependent augmentation. Metric learning aims to learn feature representations to reflect the semantic distance of data. For hand pose estimation, the distribution of augmented hand poses can be regulated by managing the distribution of feature representations. Meanwhile, hand-dependent augmentation is specifically designed for hand pose estimation to prevent semantically meaningless hand poses from being generated (e.g., hands generated by simple interpolation between both hands). Further, we demonstrate the effectiveness of the proposed technique using two well-known hand pose datasets: STB and RHD. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | 3D HAND | - |
dc.title | Implicit Semantic Data Augmentation for Hand Pose Estimation | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Cho, Hyeonjoong | - |
dc.identifier.doi | 10.1109/ACCESS.2022.3197749 | - |
dc.identifier.scopusid | 2-s2.0-85136089654 | - |
dc.identifier.wosid | 000843552000001 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.10, pp.84680 - 84688 | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 10 | - |
dc.citation.startPage | 84680 | - |
dc.citation.endPage | 84688 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordPlus | 3D HAND | - |
dc.subject.keywordAuthor | Data models | - |
dc.subject.keywordAuthor | Hand pose estimation | - |
dc.subject.keywordAuthor | Interpolation | - |
dc.subject.keywordAuthor | Neural networks | - |
dc.subject.keywordAuthor | Pose estimation | - |
dc.subject.keywordAuthor | Semantics | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Training data | - |
dc.subject.keywordAuthor | data augmentation | - |
dc.subject.keywordAuthor | feature learning | - |
dc.subject.keywordAuthor | semantic learning | - |
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.