Navigating News Programs in Large TV-Streams: A Knowledge-Based Approach
The different uses of large TV streams have continued to diversify since the appearance of digital TV. For conveniently retrieving and navigating in TV streams, users are often interested in new content-based multimedia applications of high added value such as Interactive TV, Video on Demand (VoD), YouTube or Dailymotion. These applications offer fast and easy access to best explore a particular TV program. So, the automatic process of TV program identification and their internal segmentation facilitate the availability of these programs. Therefore, it is necessary at first, to be able to retrieve a particular program within a large TV stream and secondly segment this program into semantic units related to appropriate retrieval entities. In this paper, the major originality of the authors' approach is the use of contextual and operational characteristics of TV production/post-production rules as prior knowledge that captures the structure for recurrent TV news program content. The authors validate their approach by experiments conducted using the TRECVID dataset that demonstrate its robustness.
Year of publication: |
2016
|
---|---|
Authors: | Mahdi, Walid ; Zlitni, Tarek |
Published in: |
International Journal of Knowledge Society Research (IJKSR). - IGI Global, ISSN 1947-8437, ZDB-ID 2703513-X. - Vol. 7.2016, 1 (01.01.), p. 80-98
|
Publisher: |
IGI Global |
Subject: | Knowledge-Based Video Indexing | Multimedia Applications | TV News Navigating | TV Stream Structuring | Video Grammar |
Saved in:
Online Resource
Saved in favorites
Similar items by subject