Enhancing multimedia semantic concept mining and retrieval by incorporating negative correlations

Tao Meng, Yang Liu, Mei-Ling Shyu, Yilin Yan, Chi Min Shu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In recent years, we have witnessed a deluge of multimedia data such as texts, images, and videos. However, the research of managing and retrieving these data efficiently is still in the development stage. The conventional tag-based searching approaches suffer from noisy or incomplete tag issues. As a result, the content-based multimedia data management framework has become increasingly popular. In this research direction, multimedia high-level semantic concept mining and retrieval is one of the fastest developing research topics requesting joint efforts from researchers in both data mining and multimedia domains. To solve this problem, one great challenge is to bridge the semantic gap which is the gap between high-level concepts and low-level features. Recently, positive inter-concept correlations have been utilized to capture the context of a concept to bridge the gap. However, negative correlations have rarely been studied because of the difficulty to mine and utilize them. In this paper, a concept mining and retrieval framework utilizing negative inter-concept correlations is proposed. Several research problems such as negative correlation selection, weight estimation, and score integration are addressed. Experimental results on TRECVID 2010 benchmark data set demonstrate that the proposed framework gives promising performance.

Original languageEnglish
Title of host publicationProceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014
PublisherIEEE Computer Society
Pages28-35
Number of pages8
ISBN (Print)9781479940028
DOIs
StatePublished - Jan 1 2014
Event8th IEEE International Conference on Semantic Computing, ICSC 2014 - Newport Beach, CA, United States
Duration: Jun 16 2014Jun 18 2014

Other

Other8th IEEE International Conference on Semantic Computing, ICSC 2014
CountryUnited States
CityNewport Beach, CA
Period6/16/146/18/14

Fingerprint

Semantics
Information management
Data mining

Keywords

  • Information Integration
  • Multimedia Semantic Mining and Retrieval
  • Negative Correlations

ASJC Scopus subject areas

  • Software

Cite this

Meng, T., Liu, Y., Shyu, M-L., Yan, Y., & Shu, C. M. (2014). Enhancing multimedia semantic concept mining and retrieval by incorporating negative correlations. In Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014 (pp. 28-35). [6881998] IEEE Computer Society. https://doi.org/10.1109/ICSC.2014.30

Enhancing multimedia semantic concept mining and retrieval by incorporating negative correlations. / Meng, Tao; Liu, Yang; Shyu, Mei-Ling; Yan, Yilin; Shu, Chi Min.

Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014. IEEE Computer Society, 2014. p. 28-35 6881998.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Meng, T, Liu, Y, Shyu, M-L, Yan, Y & Shu, CM 2014, Enhancing multimedia semantic concept mining and retrieval by incorporating negative correlations. in Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014., 6881998, IEEE Computer Society, pp. 28-35, 8th IEEE International Conference on Semantic Computing, ICSC 2014, Newport Beach, CA, United States, 6/16/14. https://doi.org/10.1109/ICSC.2014.30
Meng T, Liu Y, Shyu M-L, Yan Y, Shu CM. Enhancing multimedia semantic concept mining and retrieval by incorporating negative correlations. In Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014. IEEE Computer Society. 2014. p. 28-35. 6881998 https://doi.org/10.1109/ICSC.2014.30
Meng, Tao ; Liu, Yang ; Shyu, Mei-Ling ; Yan, Yilin ; Shu, Chi Min. / Enhancing multimedia semantic concept mining and retrieval by incorporating negative correlations. Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014. IEEE Computer Society, 2014. pp. 28-35
@inproceedings{65a44e2ecf1c48c38261280fb0b5a809,
title = "Enhancing multimedia semantic concept mining and retrieval by incorporating negative correlations",
abstract = "In recent years, we have witnessed a deluge of multimedia data such as texts, images, and videos. However, the research of managing and retrieving these data efficiently is still in the development stage. The conventional tag-based searching approaches suffer from noisy or incomplete tag issues. As a result, the content-based multimedia data management framework has become increasingly popular. In this research direction, multimedia high-level semantic concept mining and retrieval is one of the fastest developing research topics requesting joint efforts from researchers in both data mining and multimedia domains. To solve this problem, one great challenge is to bridge the semantic gap which is the gap between high-level concepts and low-level features. Recently, positive inter-concept correlations have been utilized to capture the context of a concept to bridge the gap. However, negative correlations have rarely been studied because of the difficulty to mine and utilize them. In this paper, a concept mining and retrieval framework utilizing negative inter-concept correlations is proposed. Several research problems such as negative correlation selection, weight estimation, and score integration are addressed. Experimental results on TRECVID 2010 benchmark data set demonstrate that the proposed framework gives promising performance.",
keywords = "Information Integration, Multimedia Semantic Mining and Retrieval, Negative Correlations",
author = "Tao Meng and Yang Liu and Mei-Ling Shyu and Yilin Yan and Shu, {Chi Min}",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/ICSC.2014.30",
language = "English",
isbn = "9781479940028",
pages = "28--35",
booktitle = "Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Enhancing multimedia semantic concept mining and retrieval by incorporating negative correlations

AU - Meng, Tao

AU - Liu, Yang

AU - Shyu, Mei-Ling

AU - Yan, Yilin

AU - Shu, Chi Min

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In recent years, we have witnessed a deluge of multimedia data such as texts, images, and videos. However, the research of managing and retrieving these data efficiently is still in the development stage. The conventional tag-based searching approaches suffer from noisy or incomplete tag issues. As a result, the content-based multimedia data management framework has become increasingly popular. In this research direction, multimedia high-level semantic concept mining and retrieval is one of the fastest developing research topics requesting joint efforts from researchers in both data mining and multimedia domains. To solve this problem, one great challenge is to bridge the semantic gap which is the gap between high-level concepts and low-level features. Recently, positive inter-concept correlations have been utilized to capture the context of a concept to bridge the gap. However, negative correlations have rarely been studied because of the difficulty to mine and utilize them. In this paper, a concept mining and retrieval framework utilizing negative inter-concept correlations is proposed. Several research problems such as negative correlation selection, weight estimation, and score integration are addressed. Experimental results on TRECVID 2010 benchmark data set demonstrate that the proposed framework gives promising performance.

AB - In recent years, we have witnessed a deluge of multimedia data such as texts, images, and videos. However, the research of managing and retrieving these data efficiently is still in the development stage. The conventional tag-based searching approaches suffer from noisy or incomplete tag issues. As a result, the content-based multimedia data management framework has become increasingly popular. In this research direction, multimedia high-level semantic concept mining and retrieval is one of the fastest developing research topics requesting joint efforts from researchers in both data mining and multimedia domains. To solve this problem, one great challenge is to bridge the semantic gap which is the gap between high-level concepts and low-level features. Recently, positive inter-concept correlations have been utilized to capture the context of a concept to bridge the gap. However, negative correlations have rarely been studied because of the difficulty to mine and utilize them. In this paper, a concept mining and retrieval framework utilizing negative inter-concept correlations is proposed. Several research problems such as negative correlation selection, weight estimation, and score integration are addressed. Experimental results on TRECVID 2010 benchmark data set demonstrate that the proposed framework gives promising performance.

KW - Information Integration

KW - Multimedia Semantic Mining and Retrieval

KW - Negative Correlations

UR - http://www.scopus.com/inward/record.url?scp=84906978998&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906978998&partnerID=8YFLogxK

U2 - 10.1109/ICSC.2014.30

DO - 10.1109/ICSC.2014.30

M3 - Conference contribution

SN - 9781479940028

SP - 28

EP - 35

BT - Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014

PB - IEEE Computer Society

ER -