Publications
Detailed Information
Pose transforming network: Learning to disentangle human posture in variational auto-encoded latent space
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lim, Jongin | - |
dc.contributor.author | Yoo, Youngjoon | - |
dc.contributor.author | Heo, Byeongho | - |
dc.contributor.author | Choi, Jin Young | - |
dc.creator | 최진영 | - |
dc.date.accessioned | 2019-04-25T01:22:47Z | - |
dc.date.available | 2020-04-05T01:22:47Z | - |
dc.date.created | 2019-07-17 | - |
dc.date.created | 2019-07-17 | - |
dc.date.issued | 2018-09 | - |
dc.identifier.citation | Pattern Recognition Letters, Vol.112, pp.91-97 | - |
dc.identifier.issn | 0167-8655 | - |
dc.identifier.uri | https://hdl.handle.net/10371/149286 | - |
dc.description.abstract | This paper proposes a novel deep conditional generative model for human pose transforms. To generate the desired pose-transformed images from a single image, a variational inference model is formulated to disentangle human posture semantics from image identity (human personality, background etc.) in variational auto-encoded latent space. A deep learning architecture is then proposed to realize the formulated variational inference model. In addition, a new loss function for the proposed training method is designed to enable pose information and identity information to be separated completely in the latent space. The proposed model is validated experimentally by demonstrating its pose-transforming capability, outperforming the existing conditional generative model. (c) 2018 Elsevier B.V. All rights reserved. | - |
dc.language | 영어 | - |
dc.language.iso | en | en |
dc.publisher | Elsevier BV | - |
dc.title | Pose transforming network: Learning to disentangle human posture in variational auto-encoded latent space | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.patrec.2018.06.020 | - |
dc.citation.journaltitle | Pattern Recognition Letters | - |
dc.identifier.wosid | 000443950800013 | - |
dc.identifier.scopusid | 2-s2.0-85048799130 | - |
dc.description.srnd | OAIID:RECH_ACHV_DSTSH_NO:T201806919 | - |
dc.description.srnd | RECH_ACHV_FG:RR00200001 | - |
dc.description.srnd | ADJUST_YN: | - |
dc.description.srnd | EMP_ID:A004911 | - |
dc.description.srnd | CITE_RATE:1.952 | - |
dc.description.srnd | FILENAME:1-s2.0-S0167865518302678-main.pdf | - |
dc.description.srnd | DEPT_NM:전기·정보공학부 | - |
dc.description.srnd | EMAIL:jychoi@snu.ac.kr | - |
dc.description.srnd | SCOPUS_YN:Y | - |
dc.description.srnd | FILEURL:https://srnd.snu.ac.kr/eXrepEIR/fws/file/0583983a-b02c-4742-92eb-c016179c3752/link | - |
dc.citation.endpage | 97 | - |
dc.citation.startpage | 91 | - |
dc.citation.volume | 112 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Choi, Jin Young | - |
dc.identifier.srnd | T201806919 | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.subject.keywordAuthor | Human pose transform | - |
dc.subject.keywordAuthor | Disentangle hidden factors in latent space | - |
dc.subject.keywordAuthor | Generative model | - |
dc.subject.keywordAuthor | Variational auto-encoder | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.