Local Topology Preserved Tensor Models for Graph Matching

Jiufeng Zhou; Hong Yan; Yuan Zhu

doi:10.1109/SMC.2015.376

Local Topology Preserved Tensor Models for Graph Matching

Jiufeng Zhou, Hong Yan, Yuan Zhu^*

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Citations (Scopus)

Abstract

This paper proposes local topology preserved features in graph matching problem based on tensor technique. Many tensor based works paid much attention on catching many invariant feature tuples while local information for every single point to improve matching performance is also important. Here our proposed Local Topology Preserved Tensor (LTPT) models not only take into account of the neighbor structure but also employ the three-order tensor technique to keep the geometric consistency. Extensive experiments on the synthetic and real datasets show that LTPT performs better than the state-of-The-Art graph matching methods.

Original language	English
Title of host publication	Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015
Publisher	IEEE
Pages	2153-2157
ISBN (Print)	9781479986965
DOIs	https://doi.org/10.1109/SMC.2015.376
Publication status	Published - 12 Jan 2016
Event	2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2015) - City University of Hong Kong, Hong Kong, China Duration: 9 Oct 2015 → 12 Oct 2015

Conference

Conference	2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2015)
Place	Hong Kong, China
Period	9/10/15 → 12/10/15

Research Keywords

geometric invariant
graph matching
Local topology preserved features
tensor technique

Access Output

10.1109/SMC.2015.376

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{d2c550a342f549cd91533f516bc9dff7,

title = "Local Topology Preserved Tensor Models for Graph Matching",

abstract = "This paper proposes local topology preserved features in graph matching problem based on tensor technique. Many tensor based works paid much attention on catching many invariant feature tuples while local information for every single point to improve matching performance is also important. Here our proposed Local Topology Preserved Tensor (LTPT) models not only take into account of the neighbor structure but also employ the three-order tensor technique to keep the geometric consistency. Extensive experiments on the synthetic and real datasets show that LTPT performs better than the state-of-The-Art graph matching methods.",

keywords = "geometric invariant, graph matching, Local topology preserved features, tensor technique",

author = "Jiufeng Zhou and Hong Yan and Yuan Zhu",

year = "2016",

month = jan,

day = "12",

doi = "10.1109/SMC.2015.376",

language = "English",

isbn = "9781479986965",

pages = "2153--2157",

booktitle = "Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015",

publisher = "IEEE",

address = "United States",

note = "2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2015) ; Conference date: 09-10-2015 Through 12-10-2015",

}

Local Topology Preserved Tensor Models for Graph Matching. / Zhou, Jiufeng; Yan, Hong; Zhu, Yuan.
Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015. IEEE, 2016. p. 2153-2157 7379508.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Local Topology Preserved Tensor Models for Graph Matching

AU - Zhou, Jiufeng

AU - Yan, Hong

AU - Zhu, Yuan

PY - 2016/1/12

Y1 - 2016/1/12

N2 - This paper proposes local topology preserved features in graph matching problem based on tensor technique. Many tensor based works paid much attention on catching many invariant feature tuples while local information for every single point to improve matching performance is also important. Here our proposed Local Topology Preserved Tensor (LTPT) models not only take into account of the neighbor structure but also employ the three-order tensor technique to keep the geometric consistency. Extensive experiments on the synthetic and real datasets show that LTPT performs better than the state-of-The-Art graph matching methods.

AB - This paper proposes local topology preserved features in graph matching problem based on tensor technique. Many tensor based works paid much attention on catching many invariant feature tuples while local information for every single point to improve matching performance is also important. Here our proposed Local Topology Preserved Tensor (LTPT) models not only take into account of the neighbor structure but also employ the three-order tensor technique to keep the geometric consistency. Extensive experiments on the synthetic and real datasets show that LTPT performs better than the state-of-The-Art graph matching methods.

KW - geometric invariant

KW - graph matching

KW - Local topology preserved features

KW - tensor technique

UR - http://www.scopus.com/inward/record.url?scp=84964412328&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84964412328&origin=recordpage

U2 - 10.1109/SMC.2015.376

DO - 10.1109/SMC.2015.376

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781479986965

SP - 2153

EP - 2157

BT - Proceedings - 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015

PB - IEEE

T2 - 2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2015)

Y2 - 9 October 2015 through 12 October 2015

ER -

Local Topology Preserved Tensor Models for Graph Matching

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this