Utilizing Indirect Associations in Multimedia Semantic Retrieval

Hsin Yu Ha, Shu Ching Chen, Mei-Ling Shyu

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

4 Citations (Scopus)

Abstract

Technological developments have lead to the propagation of massive amounts of data in the form of text, image, audio, and video. The unstoppable trend draws researchers' attention to develop approaches to efficiently retrieve and manage multimedia data. The inadequacy of keyword-based search in multimedia data retrieval due to non-existent or incomplete text annotations has called for the development of a contentbased multimedia data management framework. Specifically, detecting high-level semantic concepts is one of the rapidly growing topics in this regard. In order to thoroughly identify semantic concepts in data which have different representations and are derived from different modalities, both positive and negative inter-concept correlations have been recently studied and explored to enhance the re-ranking performance. In this paper, an indirect association rule mining (IARM) approach is introduced to reveal the hidden correlation among semantic concepts. The effectiveness of IARM is evaluated by Multiple Correspondence Analysis (MCA). Furthermore, normalization and score integration are performed to achieve the optimal classification results. The TRECVID 2011 benchmark dataset is used to show the effectiveness of the proposed IARM factor in the re-ranking process.

Original languageEnglish (US)
Title of host publicationProceedings - 2015 IEEE International Conference on Multimedia Big Data, BigMM 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages72-79
Number of pages8
ISBN (Print)9781479986880
DOIs
StatePublished - Jul 9 2015
Event1st IEEE International Conference on Multimedia Big Data, BigMM 2015 - Beijing, China
Duration: Apr 20 2015Apr 22 2015

Other

Other1st IEEE International Conference on Multimedia Big Data, BigMM 2015
CountryChina
CityBeijing
Period4/20/154/22/15

Fingerprint

Association rules
Semantics
Information management

Keywords

  • Concept Mining
  • Indirect Association Rule Mining (IARM)
  • Multimedia Data
  • Re-ranking
  • Semantic Concept Detection

ASJC Scopus subject areas

  • Information Systems
  • Media Technology

Cite this

Ha, H. Y., Chen, S. C., & Shyu, M-L. (2015). Utilizing Indirect Associations in Multimedia Semantic Retrieval. In Proceedings - 2015 IEEE International Conference on Multimedia Big Data, BigMM 2015 (pp. 72-79). [7153858] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BigMM.2015.89

Utilizing Indirect Associations in Multimedia Semantic Retrieval. / Ha, Hsin Yu; Chen, Shu Ching; Shyu, Mei-Ling.

Proceedings - 2015 IEEE International Conference on Multimedia Big Data, BigMM 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 72-79 7153858.

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

Ha, HY, Chen, SC & Shyu, M-L 2015, Utilizing Indirect Associations in Multimedia Semantic Retrieval. in Proceedings - 2015 IEEE International Conference on Multimedia Big Data, BigMM 2015., 7153858, Institute of Electrical and Electronics Engineers Inc., pp. 72-79, 1st IEEE International Conference on Multimedia Big Data, BigMM 2015, Beijing, China, 4/20/15. https://doi.org/10.1109/BigMM.2015.89
Ha HY, Chen SC, Shyu M-L. Utilizing Indirect Associations in Multimedia Semantic Retrieval. In Proceedings - 2015 IEEE International Conference on Multimedia Big Data, BigMM 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 72-79. 7153858 https://doi.org/10.1109/BigMM.2015.89
Ha, Hsin Yu ; Chen, Shu Ching ; Shyu, Mei-Ling. / Utilizing Indirect Associations in Multimedia Semantic Retrieval. Proceedings - 2015 IEEE International Conference on Multimedia Big Data, BigMM 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 72-79
@inproceedings{ea49e82d77364cf4b3feb4ba2347dcc0,
title = "Utilizing Indirect Associations in Multimedia Semantic Retrieval",
abstract = "Technological developments have lead to the propagation of massive amounts of data in the form of text, image, audio, and video. The unstoppable trend draws researchers' attention to develop approaches to efficiently retrieve and manage multimedia data. The inadequacy of keyword-based search in multimedia data retrieval due to non-existent or incomplete text annotations has called for the development of a contentbased multimedia data management framework. Specifically, detecting high-level semantic concepts is one of the rapidly growing topics in this regard. In order to thoroughly identify semantic concepts in data which have different representations and are derived from different modalities, both positive and negative inter-concept correlations have been recently studied and explored to enhance the re-ranking performance. In this paper, an indirect association rule mining (IARM) approach is introduced to reveal the hidden correlation among semantic concepts. The effectiveness of IARM is evaluated by Multiple Correspondence Analysis (MCA). Furthermore, normalization and score integration are performed to achieve the optimal classification results. The TRECVID 2011 benchmark dataset is used to show the effectiveness of the proposed IARM factor in the re-ranking process.",
keywords = "Concept Mining, Indirect Association Rule Mining (IARM), Multimedia Data, Re-ranking, Semantic Concept Detection",
author = "Ha, {Hsin Yu} and Chen, {Shu Ching} and Mei-Ling Shyu",
year = "2015",
month = "7",
day = "9",
doi = "10.1109/BigMM.2015.89",
language = "English (US)",
isbn = "9781479986880",
pages = "72--79",
booktitle = "Proceedings - 2015 IEEE International Conference on Multimedia Big Data, BigMM 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Utilizing Indirect Associations in Multimedia Semantic Retrieval

AU - Ha, Hsin Yu

AU - Chen, Shu Ching

AU - Shyu, Mei-Ling

PY - 2015/7/9

Y1 - 2015/7/9

N2 - Technological developments have lead to the propagation of massive amounts of data in the form of text, image, audio, and video. The unstoppable trend draws researchers' attention to develop approaches to efficiently retrieve and manage multimedia data. The inadequacy of keyword-based search in multimedia data retrieval due to non-existent or incomplete text annotations has called for the development of a contentbased multimedia data management framework. Specifically, detecting high-level semantic concepts is one of the rapidly growing topics in this regard. In order to thoroughly identify semantic concepts in data which have different representations and are derived from different modalities, both positive and negative inter-concept correlations have been recently studied and explored to enhance the re-ranking performance. In this paper, an indirect association rule mining (IARM) approach is introduced to reveal the hidden correlation among semantic concepts. The effectiveness of IARM is evaluated by Multiple Correspondence Analysis (MCA). Furthermore, normalization and score integration are performed to achieve the optimal classification results. The TRECVID 2011 benchmark dataset is used to show the effectiveness of the proposed IARM factor in the re-ranking process.

AB - Technological developments have lead to the propagation of massive amounts of data in the form of text, image, audio, and video. The unstoppable trend draws researchers' attention to develop approaches to efficiently retrieve and manage multimedia data. The inadequacy of keyword-based search in multimedia data retrieval due to non-existent or incomplete text annotations has called for the development of a contentbased multimedia data management framework. Specifically, detecting high-level semantic concepts is one of the rapidly growing topics in this regard. In order to thoroughly identify semantic concepts in data which have different representations and are derived from different modalities, both positive and negative inter-concept correlations have been recently studied and explored to enhance the re-ranking performance. In this paper, an indirect association rule mining (IARM) approach is introduced to reveal the hidden correlation among semantic concepts. The effectiveness of IARM is evaluated by Multiple Correspondence Analysis (MCA). Furthermore, normalization and score integration are performed to achieve the optimal classification results. The TRECVID 2011 benchmark dataset is used to show the effectiveness of the proposed IARM factor in the re-ranking process.

KW - Concept Mining

KW - Indirect Association Rule Mining (IARM)

KW - Multimedia Data

KW - Re-ranking

KW - Semantic Concept Detection

UR - http://www.scopus.com/inward/record.url?scp=84941253792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941253792&partnerID=8YFLogxK

U2 - 10.1109/BigMM.2015.89

DO - 10.1109/BigMM.2015.89

M3 - Conference contribution

SN - 9781479986880

SP - 72

EP - 79

BT - Proceedings - 2015 IEEE International Conference on Multimedia Big Data, BigMM 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -