Joint Human Pose Estimation and Instance Segmentation with PosePlusSeg
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ahmad, Niaz | - |
dc.contributor.author | Khan, Jawad | - |
dc.contributor.author | Kim, Jeremy Yuhyun | - |
dc.contributor.author | Lee, Youngmoon | - |
dc.date.accessioned | 2023-07-05T05:33:17Z | - |
dc.date.available | 2023-07-05T05:33:17Z | - |
dc.date.issued | 2023-02 | - |
dc.identifier.issn | 2159-5399 | - |
dc.identifier.issn | 2374-3468 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/112953 | - |
dc.description.abstract | Despite the advances in multi-person pose estimation, state-of-the-art techniques only deliver the human pose structure. Yet, they do not leverage the keypoints of human pose to deliver whole-body shape information for human instance segmentation. This paper presents PosePlusSeg, a joint model designed for both human pose estimation and instance segmentation. For pose estimation, PosePlusSeg first takes a bottom-up approach to detect the soft and hard keypoints of individuals by producing a strong keypoint heat map, then improves the keypoint detection confidence score by producing a body heat map. For instance segmentation, PosePlusSeg generates a mask offset where keypoint is defined as a centroid for the pixels in the embedding space, enabling instance-level segmentation for the human class. Finally, we propose a new pose and instance segmentation algorithm that enables PosePlusSeg to determine the joint structure of the human pose and instance segmentation. Experiments using the COCO challenging dataset demonstrate that PosePlusSeg copes better with challenging scenarios, like occlusions, entangled limbs, and overlapped people. PosePlusSeg outperforms state-of-the-art detection-based approaches achieving a 0.728 mAP for human pose estimation and a 0.445 mAP for instance segmentation. Code has been made available at https://github.com/RaiseLab/PosePlusSeg. | - |
dc.format.extent | 8 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE | - |
dc.title | Joint Human Pose Estimation and Instance Segmentation with PosePlusSeg | - |
dc.type | Article | - |
dc.publisher.location | 미국 | - |
dc.identifier.doi | 10.1609/aaai.v36i1.19880 | - |
dc.identifier.wosid | 000893636200008 | - |
dc.identifier.bibliographicCitation | The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), v.36, no.1, pp 69 - 76 | - |
dc.citation.title | The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22) | - |
dc.citation.volume | 36 | - |
dc.citation.number | 1 | - |
dc.citation.startPage | 69 | - |
dc.citation.endPage | 76 | - |
dc.type.docType | Proceedings Paper | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scie | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.subject.keywordAuthor | Computer Vision (CV) | - |
dc.subject.keywordAuthor | Machine Learning (ML) | - |
dc.subject.keywordAuthor | Intelligent Robotics (ROB) | - |
dc.subject.keywordAuthor | Humans And AI (HAI) | - |
dc.identifier.url | https://ojs.aaai.org/index.php/AAAI/article/view/19880 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
55 Hanyangdeahak-ro, Sangnok-gu, Ansan, Gyeonggi-do, 15588, Korea+82-31-400-4269 sweetbrain@hanyang.ac.kr
COPYRIGHT © 2021 HANYANG 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.