Compositional interaction descriptor for human interaction recognition

Nam Gyu Cho, Se Ho Park, Jeong Seon Park, Unsang Park, Seong Whan Lee

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this paper, we address the problem of human interaction recognition. We propose a novel compositional interaction descriptor to represent complex human interactions containing high intra and inter-class variations. The compositional interaction descriptor represents motion relationships on individual, local, and global levels to build a highly discriminative description. We evaluate the proposed method using UT-Interaction and BIT-Interaction public benchmark datasets. Experimental results demonstrate that the performance of the proposed approach is on a par with previous methods.

Original languageEnglish
Pages (from-to)169-181
Number of pages13
JournalNeurocomputing
Volume267
DOIs
Publication statusPublished - 2017 Dec 6

Fingerprint

Benchmarking
Datasets
2-(4-ethoxybenzyl)-1-diethylaminoethyl-5-isothiocyanatobenzimidazole

Keywords

  • Compositional interaction descriptor
  • Human interaction recognition
  • Human motion analysis

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence

Cite this

Compositional interaction descriptor for human interaction recognition. / Cho, Nam Gyu; Park, Se Ho; Park, Jeong Seon; Park, Unsang; Lee, Seong Whan.

In: Neurocomputing, Vol. 267, 06.12.2017, p. 169-181.

Research output: Contribution to journalArticle

Cho, Nam Gyu ; Park, Se Ho ; Park, Jeong Seon ; Park, Unsang ; Lee, Seong Whan. / Compositional interaction descriptor for human interaction recognition. In: Neurocomputing. 2017 ; Vol. 267. pp. 169-181.
@article{7b43eee931d64a8fb0a51262bd951faa,
title = "Compositional interaction descriptor for human interaction recognition",
abstract = "In this paper, we address the problem of human interaction recognition. We propose a novel compositional interaction descriptor to represent complex human interactions containing high intra and inter-class variations. The compositional interaction descriptor represents motion relationships on individual, local, and global levels to build a highly discriminative description. We evaluate the proposed method using UT-Interaction and BIT-Interaction public benchmark datasets. Experimental results demonstrate that the performance of the proposed approach is on a par with previous methods.",
keywords = "Compositional interaction descriptor, Human interaction recognition, Human motion analysis",
author = "Cho, {Nam Gyu} and Park, {Se Ho} and Park, {Jeong Seon} and Unsang Park and Lee, {Seong Whan}",
year = "2017",
month = "12",
day = "6",
doi = "10.1016/j.neucom.2017.06.009",
language = "English",
volume = "267",
pages = "169--181",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

TY - JOUR

T1 - Compositional interaction descriptor for human interaction recognition

AU - Cho, Nam Gyu

AU - Park, Se Ho

AU - Park, Jeong Seon

AU - Park, Unsang

AU - Lee, Seong Whan

PY - 2017/12/6

Y1 - 2017/12/6

N2 - In this paper, we address the problem of human interaction recognition. We propose a novel compositional interaction descriptor to represent complex human interactions containing high intra and inter-class variations. The compositional interaction descriptor represents motion relationships on individual, local, and global levels to build a highly discriminative description. We evaluate the proposed method using UT-Interaction and BIT-Interaction public benchmark datasets. Experimental results demonstrate that the performance of the proposed approach is on a par with previous methods.

AB - In this paper, we address the problem of human interaction recognition. We propose a novel compositional interaction descriptor to represent complex human interactions containing high intra and inter-class variations. The compositional interaction descriptor represents motion relationships on individual, local, and global levels to build a highly discriminative description. We evaluate the proposed method using UT-Interaction and BIT-Interaction public benchmark datasets. Experimental results demonstrate that the performance of the proposed approach is on a par with previous methods.

KW - Compositional interaction descriptor

KW - Human interaction recognition

KW - Human motion analysis

UR - http://www.scopus.com/inward/record.url?scp=85021189850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021189850&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2017.06.009

DO - 10.1016/j.neucom.2017.06.009

M3 - Article

AN - SCOPUS:85021189850

VL - 267

SP - 169

EP - 181

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -