With the development of internet technology, traditional TV news providers start sharing theirs news videos on the Web. As the number of TV news videos on the Web is constantly increasing, there is an impending need for effective mechanisms that are able to reduce the navigational overhead significantly with a given collection of TV news videos. Naturally, a TV news video contains a series of stories that are not related to each other, and thus building indexing structures based on the entire contents of it might be ineffective. An alternative and more promising strategy is to first find topic boundaries in a given news video based on topical coherence, and then build index structures for each coherent unit. Thus, the main goal of this paper is to develop an effective technique to detect topic boundaries of a given news video. The topic boundaries identified by our algorithm are then used to build indexing structures in order to support effective navigation guides and searches. The proposed method in this paper leverages Wikipedia to map the original contents of a news video from the keyword-space into the concept-space, and finds topic boundaries by using the contents represented in the concept-space. The experimental results show that the proposed technique provides significant precision gains in finding topic boundaries of a news video.
목차
Abstract 1. Introduction 1.1. Contributions of this Paper 2. Problem Statement 3. Background 3.1. Wikipedia-based Keyword-Concept Matrix 3.2. Wikipedia-based Semantic Interpreter 4. Algorithm 4.1. Preliminary 4.2. Step 1: Mapping from the Keyword-Space into the Concept-Space 4.3. Step 2: Detecting Topic Boundaries in the Concept-space 5. Experiment 5.1. Experimental Setup 5.2. Results and Discussion 6. Conclusion Acknowledgements References
보안공학연구지원센터(IJSEIA) [Science & Engineering Research Support Center, Republic of Korea(IJSEIA)]
설립연도
2006
분야
공학>컴퓨터학
소개
1. 보안공학에 대한 각종 조사 및 연구
2. 보안공학에 대한 응용기술 연구 및 발표
3. 보안공학에 관한 각종 학술 발표회 및 전시회 개최
4. 보안공학 기술의 상호 협조 및 정보교환
5. 보안공학에 관한 표준화 사업 및 규격의 제정
6. 보안공학에 관한 산학연 협동의 증진
7. 국제적 학술 교류 및 기술 협력
8. 보안공학에 관한 논문지 발간
9. 기타 본 회 목적 달성에 필요한 사업
간행물
간행물명
International Journal of Software Engineering and Its Applications
간기
월간
pISSN
1738-9984
수록기간
2008~2016
등재여부
SCOPUS
십진분류
KDC 505DDC 605
이 권호 내 다른 논문 / International Journal of Software Engineering and Its Applications Vol.8 No.6