Please use this identifier to cite or link to this item: http://tainguyenso.dut.udn.vn/handle/DUT/4125
Title: 3D human pose estimation with simple self-supervised learning
Authors: Pham, Le Minh Hoang
Keywords: Deep learning;Squeeze and Excitation Network;SE-net
Issue Date: 2020
Publisher: Trường Đại học Bách khoa - Đại học Đà Nẵng
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.
Description: 
DA.FA.20.027 ; 58 p.
URI: http://tainguyenso.dut.udn.vn/handle/DUT/4125
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 full item record

CORE Recommender

Google ScholarTM

Check


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