HME-KG: A method of constructing the human motion encoding knowledge graph based on a hierarchical motion model

Qi Liu; Tianyu Huang; Xiangchen Li

doi:10.1142/S1793962324500326

HME-KG: A method of constructing the human motion encoding knowledge graph based on a hierarchical motion model

Qi Liu, Tianyu Huang^*, Xiangchen Li

^*Corresponding author for this work

School of Computer Science and Technology

Research output: Contribution to journal › Article › peer-review

Abstract

The diversity, infinity, and nonuniform description of human motion make it challenging for computers to understand human activities. To explore and reuse captured human motion data, this work defines a more comprehensive hierarchical theoretical model of human motion and proposes a standard human posture encoding scheme. We construct a domain knowledge graph (DKG) named the human motion encoding knowledge graph (HME-KG) based on posture codes and action labels. Community detection, similarity analysis, and centrality analysis are used to explore the potential value of motion data. This paper conducts an evaluation and visualization of HME-KG.

Original language	English
Article number	2450032
Journal	International Journal of Modeling, Simulation, and Scientific Computing
Volume	15
Issue number	3
DOIs	https://doi.org/10.1142/S1793962324500326
Publication status	Published - 1 Jun 2024

Keywords

Human motion encoding
encoding knowledge graph
graph visualization
hierarchical motion model

Access to Document

10.1142/S1793962324500326

Cite this

@article{6c945c912bcf4194b0259ac28d81b3cc,

title = "HME-KG: A method of constructing the human motion encoding knowledge graph based on a hierarchical motion model",

abstract = "The diversity, infinity, and nonuniform description of human motion make it challenging for computers to understand human activities. To explore and reuse captured human motion data, this work defines a more comprehensive hierarchical theoretical model of human motion and proposes a standard human posture encoding scheme. We construct a domain knowledge graph (DKG) named the human motion encoding knowledge graph (HME-KG) based on posture codes and action labels. Community detection, similarity analysis, and centrality analysis are used to explore the potential value of motion data. This paper conducts an evaluation and visualization of HME-KG.",

keywords = "Human motion encoding, encoding knowledge graph, graph visualization, hierarchical motion model",

author = "Qi Liu and Tianyu Huang and Xiangchen Li",

note = "Publisher Copyright: {\textcopyright} 2024 The Author(s).",

year = "2024",

month = jun,

day = "1",

doi = "10.1142/S1793962324500326",

language = "English",

volume = "15",

journal = "International Journal of Modeling, Simulation, and Scientific Computing",

issn = "1793-9623",

publisher = "World Scientific",

number = "3",

}

TY - JOUR

T1 - HME-KG

T2 - A method of constructing the human motion encoding knowledge graph based on a hierarchical motion model

AU - Liu, Qi

AU - Huang, Tianyu

AU - Li, Xiangchen

PY - 2024/6/1

Y1 - 2024/6/1

N2 - The diversity, infinity, and nonuniform description of human motion make it challenging for computers to understand human activities. To explore and reuse captured human motion data, this work defines a more comprehensive hierarchical theoretical model of human motion and proposes a standard human posture encoding scheme. We construct a domain knowledge graph (DKG) named the human motion encoding knowledge graph (HME-KG) based on posture codes and action labels. Community detection, similarity analysis, and centrality analysis are used to explore the potential value of motion data. This paper conducts an evaluation and visualization of HME-KG.

AB - The diversity, infinity, and nonuniform description of human motion make it challenging for computers to understand human activities. To explore and reuse captured human motion data, this work defines a more comprehensive hierarchical theoretical model of human motion and proposes a standard human posture encoding scheme. We construct a domain knowledge graph (DKG) named the human motion encoding knowledge graph (HME-KG) based on posture codes and action labels. Community detection, similarity analysis, and centrality analysis are used to explore the potential value of motion data. This paper conducts an evaluation and visualization of HME-KG.

KW - Human motion encoding

KW - encoding knowledge graph

KW - graph visualization

KW - hierarchical motion model

UR - http://www.scopus.com/inward/record.url?scp=85192865467&partnerID=8YFLogxK

U2 - 10.1142/S1793962324500326

DO - 10.1142/S1793962324500326

M3 - Article

AN - SCOPUS:85192865467

SN - 1793-9623

VL - 15

JO - International Journal of Modeling, Simulation, and Scientific Computing

JF - International Journal of Modeling, Simulation, and Scientific Computing

IS - 3

M1 - 2450032

ER -

HME-KG: A method of constructing the human motion encoding knowledge graph based on a hierarchical motion model

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this