Semantic video model for content-based retrieval

Jia Ling Koh, Chin Sung Lee, Arbee L P Chen

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Traditional research on video data retrieval follows two general approaches. One is based on text annotation and the other on content-based comparison. However, these approaches do not fully make use of the meaning implied in a video stream. To improve these approaches, a semantic video model cooperated with a knowledge database is studied. In this paper, we propose a new semantic video model and focus on presenting the semantic meaning implied in a video. According to the granularity of the meaning implied in a video, a five-level layered structure to model a video stream is proposed. A mechanism is also provided to construct the five levels based on the knowledge categories defined in the knowledge database. The five-level layered structure consists of raw-data levels and semantic-data levels. A uniform semantics representation is proposed to represent the semantic-data levels. This uniform semantics representation allows measuring the similarity of two video streams with different duration. Then an interactive interface can provide browsing and querying video data efficiently through the uniform semantics representation.

Original languageEnglish
Pages (from-to)472-478
Number of pages7
JournalInternational Conference on Multimedia Computing and Systems -Proceedings
Volume2
Publication statusPublished - 1999

Fingerprint

Content based retrieval
Semantics

ASJC Scopus subject areas

  • Computer Science(all)
  • Engineering(all)

Cite this

Semantic video model for content-based retrieval. / Koh, Jia Ling; Lee, Chin Sung; Chen, Arbee L P.

In: International Conference on Multimedia Computing and Systems -Proceedings, Vol. 2, 1999, p. 472-478.

Research output: Contribution to journalArticle

@article{7d641a18373d448bae23b51cc26d9337,
title = "Semantic video model for content-based retrieval",
abstract = "Traditional research on video data retrieval follows two general approaches. One is based on text annotation and the other on content-based comparison. However, these approaches do not fully make use of the meaning implied in a video stream. To improve these approaches, a semantic video model cooperated with a knowledge database is studied. In this paper, we propose a new semantic video model and focus on presenting the semantic meaning implied in a video. According to the granularity of the meaning implied in a video, a five-level layered structure to model a video stream is proposed. A mechanism is also provided to construct the five levels based on the knowledge categories defined in the knowledge database. The five-level layered structure consists of raw-data levels and semantic-data levels. A uniform semantics representation is proposed to represent the semantic-data levels. This uniform semantics representation allows measuring the similarity of two video streams with different duration. Then an interactive interface can provide browsing and querying video data efficiently through the uniform semantics representation.",
author = "Koh, {Jia Ling} and Lee, {Chin Sung} and Chen, {Arbee L P}",
year = "1999",
language = "English",
volume = "2",
pages = "472--478",
journal = "International Conference on Multimedia Computing and Systems -Proceedings",

}

TY - JOUR

T1 - Semantic video model for content-based retrieval

AU - Koh, Jia Ling

AU - Lee, Chin Sung

AU - Chen, Arbee L P

PY - 1999

Y1 - 1999

N2 - Traditional research on video data retrieval follows two general approaches. One is based on text annotation and the other on content-based comparison. However, these approaches do not fully make use of the meaning implied in a video stream. To improve these approaches, a semantic video model cooperated with a knowledge database is studied. In this paper, we propose a new semantic video model and focus on presenting the semantic meaning implied in a video. According to the granularity of the meaning implied in a video, a five-level layered structure to model a video stream is proposed. A mechanism is also provided to construct the five levels based on the knowledge categories defined in the knowledge database. The five-level layered structure consists of raw-data levels and semantic-data levels. A uniform semantics representation is proposed to represent the semantic-data levels. This uniform semantics representation allows measuring the similarity of two video streams with different duration. Then an interactive interface can provide browsing and querying video data efficiently through the uniform semantics representation.

AB - Traditional research on video data retrieval follows two general approaches. One is based on text annotation and the other on content-based comparison. However, these approaches do not fully make use of the meaning implied in a video stream. To improve these approaches, a semantic video model cooperated with a knowledge database is studied. In this paper, we propose a new semantic video model and focus on presenting the semantic meaning implied in a video. According to the granularity of the meaning implied in a video, a five-level layered structure to model a video stream is proposed. A mechanism is also provided to construct the five levels based on the knowledge categories defined in the knowledge database. The five-level layered structure consists of raw-data levels and semantic-data levels. A uniform semantics representation is proposed to represent the semantic-data levels. This uniform semantics representation allows measuring the similarity of two video streams with different duration. Then an interactive interface can provide browsing and querying video data efficiently through the uniform semantics representation.

UR - http://www.scopus.com/inward/record.url?scp=0032676493&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032676493&partnerID=8YFLogxK

M3 - Article

VL - 2

SP - 472

EP - 478

JO - International Conference on Multimedia Computing and Systems -Proceedings

JF - International Conference on Multimedia Computing and Systems -Proceedings

ER -