Bipolar grouping

Jiang Xu; Junsong Yuan; Ying Wu

doi:10.1109/ICME.2010.5583062

Bipolar grouping

Jiang Xu^*, Junsong Yuan, Ying Wu

^*Corresponding author for this work

Electrical and Computer Engineering

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

1 Scopus citations

Abstract

Most affinity-based grouping methods only model the inclusive relation among the data. When the data set contains a significant amount of noise data that should not be included in any clusters, these methods are likely to lead to undesired results. To address this issue, this paper presents a new approach called bipolar grouping that is targeted on extracting the groups from the data while excluding the noise. This new approach incorporates both inclusive and exclusive relations among data, and a fixed-point procedure is proposed to find the stable groups. Its effectiveness and general applicability are demonstrated in two applications, including discovering common objects in images and tracking targets in clutter.

Original language	English (US)
Title of host publication	2010 IEEE International Conference on Multimedia and Expo, ICME 2010
Pages	54-59
Number of pages	6
DOIs	https://doi.org/10.1109/ICME.2010.5583062
State	Published - Nov 22 2010
Event	2010 IEEE International Conference on Multimedia and Expo, ICME 2010 - Singapore, Singapore Duration: Jul 19 2010 → Jul 23 2010

Publication series

Name	2010 IEEE International Conference on Multimedia and Expo, ICME 2010

Other

Other	2010 IEEE International Conference on Multimedia and Expo, ICME 2010
Country/Territory	Singapore
City	Singapore
Period	7/19/10 → 7/23/10

Keywords

Bipolar grouping
Common pattern discovery
Visual object tracking

ASJC Scopus subject areas

Human-Computer Interaction
Software

Access to Document

10.1109/ICME.2010.5583062

Cite this

@inproceedings{cf00f7a583504387865ee02cd2db6d9a,

title = "Bipolar grouping",

abstract = "Most affinity-based grouping methods only model the inclusive relation among the data. When the data set contains a significant amount of noise data that should not be included in any clusters, these methods are likely to lead to undesired results. To address this issue, this paper presents a new approach called bipolar grouping that is targeted on extracting the groups from the data while excluding the noise. This new approach incorporates both inclusive and exclusive relations among data, and a fixed-point procedure is proposed to find the stable groups. Its effectiveness and general applicability are demonstrated in two applications, including discovering common objects in images and tracking targets in clutter.",

keywords = "Bipolar grouping, Common pattern discovery, Visual object tracking",

author = "Jiang Xu and Junsong Yuan and Ying Wu",

year = "2010",

month = nov,

day = "22",

doi = "10.1109/ICME.2010.5583062",

language = "English (US)",

isbn = "9781424474912",

series = "2010 IEEE International Conference on Multimedia and Expo, ICME 2010",

pages = "54--59",

booktitle = "2010 IEEE International Conference on Multimedia and Expo, ICME 2010",

note = "2010 IEEE International Conference on Multimedia and Expo, ICME 2010 ; Conference date: 19-07-2010 Through 23-07-2010",

}

TY - GEN

T1 - Bipolar grouping

AU - Xu, Jiang

AU - Yuan, Junsong

AU - Wu, Ying

PY - 2010/11/22

Y1 - 2010/11/22

N2 - Most affinity-based grouping methods only model the inclusive relation among the data. When the data set contains a significant amount of noise data that should not be included in any clusters, these methods are likely to lead to undesired results. To address this issue, this paper presents a new approach called bipolar grouping that is targeted on extracting the groups from the data while excluding the noise. This new approach incorporates both inclusive and exclusive relations among data, and a fixed-point procedure is proposed to find the stable groups. Its effectiveness and general applicability are demonstrated in two applications, including discovering common objects in images and tracking targets in clutter.

AB - Most affinity-based grouping methods only model the inclusive relation among the data. When the data set contains a significant amount of noise data that should not be included in any clusters, these methods are likely to lead to undesired results. To address this issue, this paper presents a new approach called bipolar grouping that is targeted on extracting the groups from the data while excluding the noise. This new approach incorporates both inclusive and exclusive relations among data, and a fixed-point procedure is proposed to find the stable groups. Its effectiveness and general applicability are demonstrated in two applications, including discovering common objects in images and tracking targets in clutter.

KW - Bipolar grouping

KW - Common pattern discovery

KW - Visual object tracking

UR - http://www.scopus.com/inward/record.url?scp=78349278024&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78349278024&partnerID=8YFLogxK

U2 - 10.1109/ICME.2010.5583062

DO - 10.1109/ICME.2010.5583062

M3 - Conference contribution

AN - SCOPUS:78349278024

SN - 9781424474912

T3 - 2010 IEEE International Conference on Multimedia and Expo, ICME 2010

SP - 54

EP - 59

BT - 2010 IEEE International Conference on Multimedia and Expo, ICME 2010

T2 - 2010 IEEE International Conference on Multimedia and Expo, ICME 2010

Y2 - 19 July 2010 through 23 July 2010

ER -

Bipolar grouping

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this