Please use this identifier to cite or link to this item: http://tainguyenso.dut.udn.vn/handle/DUT/4125
DC FieldValueLanguage
dc.contributor.advisorNguyen, Quang Nhu Quynh, Dr.
dc.contributor.authorPham, Le Minh Hoang
dc.date.accessioned2024-11-06T05:20:20Z-
dc.date.available2024-11-06T05:20:20Z-
dc.date.issued2020
dc.identifier.urihttp://tainguyenso.dut.udn.vn/handle/DUT/4125-
dc.descriptionDA.FA.20.027 ; 58 p.vi
dc.description.abstractRecent studies have shown remarkable advances in 3D human pose estimation from monocular images, with the help of large-scale in-door 3D datasets and ophisticated network architectures. However, the generalizability to different environments remains an elusive goal. In this work, we present a solution for single-view 3D human skeleton estimation based on deep learning method. Our network contains two separate model to fully regress and enhance the resulting poses. We utilize a newly proposed model whose name is Squeeze and Excitation Network (SE-net) as to construct our pose estimation network in order to estimate the corresponding pose from a color image; then a model consisting of several blocks of fully-connected networks and a novel semantic graph convolutional networks featuring self-supervision to reconstruct 3D human pose. We demonstrate the effectiveness of our approach on standard datasets for benchmark where we achieved comparable results to some recent state-of-the-art methods.vi
dc.language.isoenvi
dc.publisherTrường Đại học Bách khoa - Đại học Đà Nẵngvi
dc.subjectDeep learningvi
dc.subjectSqueeze and Excitation Networkvi
dc.subjectSE-netvi
dc.title3D human pose estimation with simple self-supervised learningvi
dc.typeĐồ ánvi
item.cerifentitytypePublications-
item.openairetypeĐồ án-
item.grantfulltextrestricted-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.fulltextCó toàn văn-
item.languageiso639-1en-
Appears in Collections:DA.Điện tử - Viễn thông
Files in This Item:
File Description SizeFormat Existing users please Login
7.DA.FA.20.027.PhamLeMinhHoang.pdfThuyết minh13.82 MBAdobe PDF
    Request a copy
Show simple item record

CORE Recommender

Google ScholarTM

Check


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