Compositional interaction descriptor for human interaction recognition

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

doi:10.1016/j.neucom.2017.06.009

Compositional interaction descriptor for human interaction recognition

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

Department of Artificial Intelligence

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

21 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 language	English
Pages (from-to)	169-181
Number of pages	13
Journal	Neurocomputing
Volume	267
DOIs	https://doi.org/10.1016/j.neucom.2017.06.009
Publication status	Published - 2017 Dec 6

Keywords

Compositional interaction descriptor
Human interaction recognition
Human motion analysis

ASJC Scopus subject areas

Computer Science Applications
Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/j.neucom.2017.06.009

Cite this

@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}",

note = "Funding Information: The research was supported by the Implementation of Technologies for Identification, Behavior, and Location of Human based on Sensor Network Fusion Program through the Ministry of Trade, Industry and Energy (Grant No. 10041629). Partial support was also provided by the ICT R&D program of MSIP/IITP [B0101-15-0552, Development of Predictive Visual Intelligence Technology] and Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (No. R7117-16-0157, Development of Smart Car Vision Techniques based on Deep Learning for Pedestrian Safety). Publisher Copyright: {\textcopyright} 2017 Elsevier B.V.",

year = "2017",

month = dec,

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

N1 - Funding Information: The research was supported by the Implementation of Technologies for Identification, Behavior, and Location of Human based on Sensor Network Fusion Program through the Ministry of Trade, Industry and Energy (Grant No. 10041629). Partial support was also provided by the ICT R&D program of MSIP/IITP [B0101-15-0552, Development of Predictive Visual Intelligence Technology] and Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (No. R7117-16-0157, Development of Smart Car Vision Techniques based on Deep Learning for Pedestrian Safety). Publisher Copyright: © 2017 Elsevier B.V.

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

U2 - 10.1016/j.neucom.2017.06.009

DO - 10.1016/j.neucom.2017.06.009

M3 - Article

AN - SCOPUS:85021189850

SN - 0925-2312

VL - 267

SP - 169

EP - 181

JO - Neurocomputing

JF - Neurocomputing

ER -

Compositional interaction descriptor for human interaction recognition

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this