Variant Graph Convolutional Networks for Skeleton-Based Hand Action Recognition

Khin Sabai Htwe; Hiroshi Watanabe

doi:10.1109/GCCE53005.2021.9621997

Variant Graph Convolutional Networks for Skeleton-Based Hand Action Recognition

Khin Sabai Htwe, Hiroshi Watanabe

School of Fundamental Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Graph convolutional network is widely used in skeleton-based applications such as action recognition. In this paper, a Variant Graph Convolutional Network (VGCN) is proposed to learn not to be constrained of the physical connections of hand structure since a predefined fixed graph structure lacks of flexibility to capture variance and different actions. With experiment on our hand actions skeleton dataset, the proposed method outperform with significance accuracy to the conventional ones.

Original language	English
Title of host publication	2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	651-652
Number of pages	2
ISBN (Electronic)	9781665436762
DOIs	https://doi.org/10.1109/GCCE53005.2021.9621997
Publication status	Published - 2021
Event	10th IEEE Global Conference on Consumer Electronics, GCCE 2021 - Kyoto, Japan Duration: 2021 Oct 12 → 2021 Oct 15

Publication series

Name	2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021

Conference

Conference	10th IEEE Global Conference on Consumer Electronics, GCCE 2021
Country/Territory	Japan
City	Kyoto
Period	21/10/12 → 21/10/15

Keywords

graph convolutional network
hand action
recognition
skeleton information
variant joints

ASJC Scopus subject areas

Computer Science Applications
Signal Processing
Biomedical Engineering
Electrical and Electronic Engineering
Media Technology
Instrumentation

Access to Document

10.1109/GCCE53005.2021.9621997

Cite this

Htwe, K. S., & Watanabe, H. (2021). Variant Graph Convolutional Networks for Skeleton-Based Hand Action Recognition. In 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021 (pp. 651-652). (2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GCCE53005.2021.9621997

Variant Graph Convolutional Networks for Skeleton-Based Hand Action Recognition. / Htwe, Khin Sabai; Watanabe, Hiroshi.

2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 651-652 (2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Htwe, KS & Watanabe, H 2021, Variant Graph Convolutional Networks for Skeleton-Based Hand Action Recognition. in 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021. 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021, Institute of Electrical and Electronics Engineers Inc., pp. 651-652, 10th IEEE Global Conference on Consumer Electronics, GCCE 2021, Kyoto, Japan, 21/10/12. https://doi.org/10.1109/GCCE53005.2021.9621997

@inproceedings{ce59296473684db29f00ddcd47edcaf1,

title = "Variant Graph Convolutional Networks for Skeleton-Based Hand Action Recognition",

abstract = "Graph convolutional network is widely used in skeleton-based applications such as action recognition. In this paper, a Variant Graph Convolutional Network (VGCN) is proposed to learn not to be constrained of the physical connections of hand structure since a predefined fixed graph structure lacks of flexibility to capture variance and different actions. With experiment on our hand actions skeleton dataset, the proposed method outperform with significance accuracy to the conventional ones.",

keywords = "graph convolutional network, hand action, recognition, skeleton information, variant joints",

author = "Htwe, {Khin Sabai} and Hiroshi Watanabe",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 10th IEEE Global Conference on Consumer Electronics, GCCE 2021 ; Conference date: 12-10-2021 Through 15-10-2021",

year = "2021",

doi = "10.1109/GCCE53005.2021.9621997",

language = "English",

series = "2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "651--652",

booktitle = "2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021",

}

TY - GEN

T1 - Variant Graph Convolutional Networks for Skeleton-Based Hand Action Recognition

AU - Htwe, Khin Sabai

AU - Watanabe, Hiroshi

PY - 2021

Y1 - 2021

N2 - Graph convolutional network is widely used in skeleton-based applications such as action recognition. In this paper, a Variant Graph Convolutional Network (VGCN) is proposed to learn not to be constrained of the physical connections of hand structure since a predefined fixed graph structure lacks of flexibility to capture variance and different actions. With experiment on our hand actions skeleton dataset, the proposed method outperform with significance accuracy to the conventional ones.

AB - Graph convolutional network is widely used in skeleton-based applications such as action recognition. In this paper, a Variant Graph Convolutional Network (VGCN) is proposed to learn not to be constrained of the physical connections of hand structure since a predefined fixed graph structure lacks of flexibility to capture variance and different actions. With experiment on our hand actions skeleton dataset, the proposed method outperform with significance accuracy to the conventional ones.

KW - graph convolutional network

KW - hand action

KW - recognition

KW - skeleton information

KW - variant joints

UR - http://www.scopus.com/inward/record.url?scp=85123478171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85123478171&partnerID=8YFLogxK

U2 - 10.1109/GCCE53005.2021.9621997

DO - 10.1109/GCCE53005.2021.9621997

M3 - Conference contribution

AN - SCOPUS:85123478171

T3 - 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021

SP - 651

EP - 652

BT - 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th IEEE Global Conference on Consumer Electronics, GCCE 2021

Y2 - 12 October 2021 through 15 October 2021

ER -

Variant Graph Convolutional Networks for Skeleton-Based Hand Action Recognition

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this