K-Partite graph reinforcement and its application in multimedia information retrieval

Yue Gao, Meng Wang, Rongrong Ji, Zhengjun Zha, Jialie Shen

Research output: Contribution to journalArticleResearchpeer-review

Abstract

In many example-based information retrieval tasks, example query actually contains multiple sub-queries. For example, in 3D object retrieval, the query is an object described by multiple views. In content-based video retrieval, the query is a video clip that contains multiple frames. Without prior knowledge, the most intuitive approach is to treat the sub-queries equally without difference. In this paper, we propose a k-partite graph reinforcement approach to fuse these sub-queries based on the to-be-retrieved database. The approach first collects the top retrieved results. These results are regarded as pseudo-relevant samples and then a k-partite graph reinforcement is performed on these samples and the query. In the reinforcement process, the weights of the sub-queries are updated by an iterative process. We present experiments on 3D object retrieval and content-based video clip retrieval, and the results demonstrate that our method effectively boosts retrieval performance.

Original languageEnglish
Pages (from-to)224-239
Number of pages16
JournalInformation Sciences
Volume194
DOIs
Publication statusPublished - 1 Jul 2012
Externally publishedYes

Fingerprint

Reinforcement
Information retrieval
Information Retrieval
Multimedia
Query
Graph in graph theory
Electric fuses
Video Retrieval
Content-based Retrieval
Retrieval
Graph
Iterative Process
Experiments
Prior Knowledge
Intuitive
Demonstrate
Experiment
Object

Cite this

Gao, Yue ; Wang, Meng ; Ji, Rongrong ; Zha, Zhengjun ; Shen, Jialie. / K-Partite graph reinforcement and its application in multimedia information retrieval. In: Information Sciences. 2012 ; Vol. 194. pp. 224-239.
@article{abf72b1af07f4c1db12786d2284c2c93,
title = "K-Partite graph reinforcement and its application in multimedia information retrieval",
abstract = "In many example-based information retrieval tasks, example query actually contains multiple sub-queries. For example, in 3D object retrieval, the query is an object described by multiple views. In content-based video retrieval, the query is a video clip that contains multiple frames. Without prior knowledge, the most intuitive approach is to treat the sub-queries equally without difference. In this paper, we propose a k-partite graph reinforcement approach to fuse these sub-queries based on the to-be-retrieved database. The approach first collects the top retrieved results. These results are regarded as pseudo-relevant samples and then a k-partite graph reinforcement is performed on these samples and the query. In the reinforcement process, the weights of the sub-queries are updated by an iterative process. We present experiments on 3D object retrieval and content-based video clip retrieval, and the results demonstrate that our method effectively boosts retrieval performance.",
keywords = "3D object retrieval, k-Partite graph reinforcement, Multimedia information retrieval, Video retrieval",
author = "Yue Gao and Meng Wang and Rongrong Ji and Zhengjun Zha and Jialie Shen",
year = "2012",
month = "7",
day = "1",
doi = "10.1016/j.ins.2012.01.003",
language = "English",
volume = "194",
pages = "224--239",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier",

}

K-Partite graph reinforcement and its application in multimedia information retrieval. / Gao, Yue; Wang, Meng; Ji, Rongrong; Zha, Zhengjun; Shen, Jialie.

In: Information Sciences, Vol. 194, 01.07.2012, p. 224-239.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - K-Partite graph reinforcement and its application in multimedia information retrieval

AU - Gao, Yue

AU - Wang, Meng

AU - Ji, Rongrong

AU - Zha, Zhengjun

AU - Shen, Jialie

PY - 2012/7/1

Y1 - 2012/7/1

N2 - In many example-based information retrieval tasks, example query actually contains multiple sub-queries. For example, in 3D object retrieval, the query is an object described by multiple views. In content-based video retrieval, the query is a video clip that contains multiple frames. Without prior knowledge, the most intuitive approach is to treat the sub-queries equally without difference. In this paper, we propose a k-partite graph reinforcement approach to fuse these sub-queries based on the to-be-retrieved database. The approach first collects the top retrieved results. These results are regarded as pseudo-relevant samples and then a k-partite graph reinforcement is performed on these samples and the query. In the reinforcement process, the weights of the sub-queries are updated by an iterative process. We present experiments on 3D object retrieval and content-based video clip retrieval, and the results demonstrate that our method effectively boosts retrieval performance.

AB - In many example-based information retrieval tasks, example query actually contains multiple sub-queries. For example, in 3D object retrieval, the query is an object described by multiple views. In content-based video retrieval, the query is a video clip that contains multiple frames. Without prior knowledge, the most intuitive approach is to treat the sub-queries equally without difference. In this paper, we propose a k-partite graph reinforcement approach to fuse these sub-queries based on the to-be-retrieved database. The approach first collects the top retrieved results. These results are regarded as pseudo-relevant samples and then a k-partite graph reinforcement is performed on these samples and the query. In the reinforcement process, the weights of the sub-queries are updated by an iterative process. We present experiments on 3D object retrieval and content-based video clip retrieval, and the results demonstrate that our method effectively boosts retrieval performance.

KW - 3D object retrieval

KW - k-Partite graph reinforcement

KW - Multimedia information retrieval

KW - Video retrieval

UR - http://www.scopus.com/inward/record.url?scp=84862815270&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2012.01.003

DO - 10.1016/j.ins.2012.01.003

M3 - Article

VL - 194

SP - 224

EP - 239

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -