View-based 3D object retrieval by bipartite graph matching

Yue Wen, Yue Gao, Richang Hong, Huanbo Luan, Qiong Liu, Jialie Shen, Rongrong Ji

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

Abstract

Bipartite graph matching has been investigated in multiple view matching for 3D object retrieval. However, existing methods employ one-to-one vertex matching scheme while more than two views may share close semantic meanings in practice. In this work, we propose a bipartite graph matching method to measure the distance between two objects based on multiple views. In the proposed method, representative views are first selected by using view clustering for each object, and the corresponding weights are given based on the cluster results. A bipartite graph is constructed by using the two groups of representative views from two compared objects. To calculate the similarity between two objects, the bipartite graph is first partitioned to several subsets, and the views in the same sub-set are with high possibility to be with similar semantic meanings. The distances between two objects within individual subsets are then assembled through the graph to obtain the final similarity. Experimental results and comparison with the state-of-the-art methods demonstrate the effectiveness of the proposed algorithm.

Original languageEnglish
Title of host publicationMM 2012 - Proceedings of the 20th ACM International Conference on Multimedia
Place of PublicationNara, Japan
PublisherAssociation for Computing Machinery (ACM)
Pages897-900
Number of pages4
ISBN (Print)9781450310895
DOIs
Publication statusPublished - 26 Dec 2012
Externally publishedYes
Event20th ACM International Conference on Multimedia, MM 2012 - Nara, Japan
Duration: 29 Oct 20122 Nov 2012

Conference

Conference20th ACM International Conference on Multimedia, MM 2012
CountryJapan
CityNara
Period29/10/122/11/12

Fingerprint

Semantics

Cite this

Wen, Y., Gao, Y., Hong, R., Luan, H., Liu, Q., Shen, J., & Ji, R. (2012). View-based 3D object retrieval by bipartite graph matching. In MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia (pp. 897-900). Nara, Japan: Association for Computing Machinery (ACM). https://doi.org/10.1145/2393347.2396341
Wen, Yue ; Gao, Yue ; Hong, Richang ; Luan, Huanbo ; Liu, Qiong ; Shen, Jialie ; Ji, Rongrong. / View-based 3D object retrieval by bipartite graph matching. MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia. Nara, Japan : Association for Computing Machinery (ACM), 2012. pp. 897-900
@inproceedings{2de4de283c3740699536de501824f111,
title = "View-based 3D object retrieval by bipartite graph matching",
abstract = "Bipartite graph matching has been investigated in multiple view matching for 3D object retrieval. However, existing methods employ one-to-one vertex matching scheme while more than two views may share close semantic meanings in practice. In this work, we propose a bipartite graph matching method to measure the distance between two objects based on multiple views. In the proposed method, representative views are first selected by using view clustering for each object, and the corresponding weights are given based on the cluster results. A bipartite graph is constructed by using the two groups of representative views from two compared objects. To calculate the similarity between two objects, the bipartite graph is first partitioned to several subsets, and the views in the same sub-set are with high possibility to be with similar semantic meanings. The distances between two objects within individual subsets are then assembled through the graph to obtain the final similarity. Experimental results and comparison with the state-of-the-art methods demonstrate the effectiveness of the proposed algorithm.",
keywords = "3D object retrieval, bipartite graph, graph matching",
author = "Yue Wen and Yue Gao and Richang Hong and Huanbo Luan and Qiong Liu and Jialie Shen and Rongrong Ji",
year = "2012",
month = "12",
day = "26",
doi = "10.1145/2393347.2396341",
language = "English",
isbn = "9781450310895",
pages = "897--900",
booktitle = "MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",

}

Wen, Y, Gao, Y, Hong, R, Luan, H, Liu, Q, Shen, J & Ji, R 2012, View-based 3D object retrieval by bipartite graph matching. in MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia. Association for Computing Machinery (ACM), Nara, Japan, pp. 897-900, 20th ACM International Conference on Multimedia, MM 2012, Nara, Japan, 29/10/12. https://doi.org/10.1145/2393347.2396341

View-based 3D object retrieval by bipartite graph matching. / Wen, Yue; Gao, Yue; Hong, Richang; Luan, Huanbo; Liu, Qiong; Shen, Jialie; Ji, Rongrong.

MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia. Nara, Japan : Association for Computing Machinery (ACM), 2012. p. 897-900.

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

TY - GEN

T1 - View-based 3D object retrieval by bipartite graph matching

AU - Wen, Yue

AU - Gao, Yue

AU - Hong, Richang

AU - Luan, Huanbo

AU - Liu, Qiong

AU - Shen, Jialie

AU - Ji, Rongrong

PY - 2012/12/26

Y1 - 2012/12/26

N2 - Bipartite graph matching has been investigated in multiple view matching for 3D object retrieval. However, existing methods employ one-to-one vertex matching scheme while more than two views may share close semantic meanings in practice. In this work, we propose a bipartite graph matching method to measure the distance between two objects based on multiple views. In the proposed method, representative views are first selected by using view clustering for each object, and the corresponding weights are given based on the cluster results. A bipartite graph is constructed by using the two groups of representative views from two compared objects. To calculate the similarity between two objects, the bipartite graph is first partitioned to several subsets, and the views in the same sub-set are with high possibility to be with similar semantic meanings. The distances between two objects within individual subsets are then assembled through the graph to obtain the final similarity. Experimental results and comparison with the state-of-the-art methods demonstrate the effectiveness of the proposed algorithm.

AB - Bipartite graph matching has been investigated in multiple view matching for 3D object retrieval. However, existing methods employ one-to-one vertex matching scheme while more than two views may share close semantic meanings in practice. In this work, we propose a bipartite graph matching method to measure the distance between two objects based on multiple views. In the proposed method, representative views are first selected by using view clustering for each object, and the corresponding weights are given based on the cluster results. A bipartite graph is constructed by using the two groups of representative views from two compared objects. To calculate the similarity between two objects, the bipartite graph is first partitioned to several subsets, and the views in the same sub-set are with high possibility to be with similar semantic meanings. The distances between two objects within individual subsets are then assembled through the graph to obtain the final similarity. Experimental results and comparison with the state-of-the-art methods demonstrate the effectiveness of the proposed algorithm.

KW - 3D object retrieval

KW - bipartite graph

KW - graph matching

UR - http://www.scopus.com/inward/record.url?scp=84871363836&partnerID=8YFLogxK

U2 - 10.1145/2393347.2396341

DO - 10.1145/2393347.2396341

M3 - Conference Paper published in Proceedings

SN - 9781450310895

SP - 897

EP - 900

BT - MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia

PB - Association for Computing Machinery (ACM)

CY - Nara, Japan

ER -

Wen Y, Gao Y, Hong R, Luan H, Liu Q, Shen J et al. View-based 3D object retrieval by bipartite graph matching. In MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia. Nara, Japan: Association for Computing Machinery (ACM). 2012. p. 897-900 https://doi.org/10.1145/2393347.2396341