Please use this identifier to cite or link to this item:
http://tainguyenso.dut.udn.vn/handle/DUT/4382
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Nguyen, Quang Nhu Quynh, Dr. | - |
dc.contributor.author | Pham, Le Minh Hoang | - |
dc.date.accessioned | 2024-04-03T06:37:58Z | - |
dc.date.available | 2024-04-03T06:37:58Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://tainguyenso.dut.udn.vn/handle/DUT/4382 | - |
dc.description | DA.FA.20.027 ; 58 p. | vi |
dc.description.abstract | Recent 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.iso | en | vi |
dc.publisher | Trường Đại học Bách khoa - Đại học Đà Nẵng | vi |
dc.subject | Deep learning | vi |
dc.subject | Squeeze and Excitation Network | vi |
dc.subject | SE-net | vi |
dc.title | 3D human pose estimation with simple self-supervised learning | vi |
dc.type | Other | vi |
Appears in Collections: | DA.Điện tử - Viễn thông |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
7.DA.FA.20.027.PhamLeMinhHoang.pdf | Thuyết minh | 13.82 MB | Adobe PDF | Sign in to read |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.