Large Scale Image Clustering with Support Vector Machine based on Visual Keywords

Tian-Tian Chang; Horace H.S. Ip; Jun Feng

doi:10.1145/1814245.1814250

Large Scale Image Clustering with Support Vector Machine based on Visual Keywords

Tian-Tian Chang, Horace H.S. Ip, Jun Feng

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

Abstract

Support Vector Machine Clustering (SVMC) is a model-based clustering method designed primarily for solving 2-class clustering problems. In this paper, we generalize the SVMC method to multi-class clustering via two different strategies, namely One-Against-All and hierarchical clustering. We applied the resulting multi-class SVMC techniques to large scale image clustering based on the visual keywords representation and Histogram Intersection Kernel. Experiments on two benchmark databases show that compared with traditional Support Vector Clustering (SVC) method, our proposed approach is particularly suited to large scale data and large number of classes clustering problems, in terms of computational efficiency and clustering quality.

Original language	English
Title of host publication	MDMKDD '10 - Proceedings of the Tenth International Workshop on Multimedia Data Mining
DOIs	https://doi.org/10.1145/1814245.1814250
Publication status	Published - 25 Jul 2010
Event	10th International Workshop on Multimedia Data Mining (MDMKDD '10) - Washington, United States Duration: 25 Jul 2010 → 25 Jul 2010

Workshop

Workshop	10th International Workshop on Multimedia Data Mining (MDMKDD '10)
Country/Territory	United States
City	Washington
Period	25/07/10 → 25/07/10

Research Keywords

Clustering
Hierarchical
Histogram Intersection Kernel
Image clustering
Multi-class
One-Against-All
Support Vector Machine
Visual keywords

Access Output

10.1145/1814245.1814250

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{02cba549048c4b04a07608a1654e3ba9,

title = "Large Scale Image Clustering with Support Vector Machine based on Visual Keywords",

abstract = "Support Vector Machine Clustering (SVMC) is a model-based clustering method designed primarily for solving 2-class clustering problems. In this paper, we generalize the SVMC method to multi-class clustering via two different strategies, namely One-Against-All and hierarchical clustering. We applied the resulting multi-class SVMC techniques to large scale image clustering based on the visual keywords representation and Histogram Intersection Kernel. Experiments on two benchmark databases show that compared with traditional Support Vector Clustering (SVC) method, our proposed approach is particularly suited to large scale data and large number of classes clustering problems, in terms of computational efficiency and clustering quality.",

keywords = "Clustering, Hierarchical, Histogram Intersection Kernel, Image clustering, Multi-class, One-Against-All, Support Vector Machine, Visual keywords",

author = "Tian-Tian Chang and Ip, {Horace H.S.} and Jun Feng",

year = "2010",

month = jul,

day = "25",

doi = "10.1145/1814245.1814250",

language = "English",

isbn = "9781450302203",

booktitle = "MDMKDD '10 - Proceedings of the Tenth International Workshop on Multimedia Data Mining",

note = "10th International Workshop on Multimedia Data Mining (MDMKDD '10) ; Conference date: 25-07-2010 Through 25-07-2010",

}

Chang, T-T, Ip, HHS & Feng, J 2010, Large Scale Image Clustering with Support Vector Machine based on Visual Keywords. in MDMKDD '10 - Proceedings of the Tenth International Workshop on Multimedia Data Mining., 5, 10th International Workshop on Multimedia Data Mining (MDMKDD '10), Washington, District of Columbia, United States, 25/07/10. https://doi.org/10.1145/1814245.1814250

Large Scale Image Clustering with Support Vector Machine based on Visual Keywords. / Chang, Tian-Tian; Ip, Horace H.S.; Feng, Jun.
MDMKDD '10 - Proceedings of the Tenth International Workshop on Multimedia Data Mining. 2010. 5.

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

TY - GEN

T1 - Large Scale Image Clustering with Support Vector Machine based on Visual Keywords

AU - Chang, Tian-Tian

AU - Ip, Horace H.S.

AU - Feng, Jun

PY - 2010/7/25

Y1 - 2010/7/25

N2 - Support Vector Machine Clustering (SVMC) is a model-based clustering method designed primarily for solving 2-class clustering problems. In this paper, we generalize the SVMC method to multi-class clustering via two different strategies, namely One-Against-All and hierarchical clustering. We applied the resulting multi-class SVMC techniques to large scale image clustering based on the visual keywords representation and Histogram Intersection Kernel. Experiments on two benchmark databases show that compared with traditional Support Vector Clustering (SVC) method, our proposed approach is particularly suited to large scale data and large number of classes clustering problems, in terms of computational efficiency and clustering quality.

AB - Support Vector Machine Clustering (SVMC) is a model-based clustering method designed primarily for solving 2-class clustering problems. In this paper, we generalize the SVMC method to multi-class clustering via two different strategies, namely One-Against-All and hierarchical clustering. We applied the resulting multi-class SVMC techniques to large scale image clustering based on the visual keywords representation and Histogram Intersection Kernel. Experiments on two benchmark databases show that compared with traditional Support Vector Clustering (SVC) method, our proposed approach is particularly suited to large scale data and large number of classes clustering problems, in terms of computational efficiency and clustering quality.

KW - Clustering

KW - Hierarchical

KW - Histogram Intersection Kernel

KW - Image clustering

KW - Multi-class

KW - One-Against-All

KW - Support Vector Machine

KW - Visual keywords

UR - http://www.scopus.com/inward/record.url?scp=77956249052&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-77956249052&origin=recordpage

U2 - 10.1145/1814245.1814250

DO - 10.1145/1814245.1814250

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

SN - 9781450302203

BT - MDMKDD '10 - Proceedings of the Tenth International Workshop on Multimedia Data Mining

T2 - 10th International Workshop on Multimedia Data Mining (MDMKDD '10)

Y2 - 25 July 2010 through 25 July 2010

ER -

Large Scale Image Clustering with Support Vector Machine based on Visual Keywords

Abstract

Workshop

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this