Use of Probabilistic Clusters Supports for Broadcast News Segmentation

Author

Di Iulio, M. ; Messina, Alberto

Author_Institution

Dept. of Comput. Sci., Univ. degli Studi di Torino, Turin

fYear

2008

fDate

1-5 Sept. 2008

Firstpage

600

Lastpage

604

Abstract

Broadcast news segmentation is a recognised important task in audiovisual archives retrieval systems. Though research is very active in the field, the problem has not been satisfactorily solved yet. This paper presents a promising novel methodology at segmenting news programmes based on a probabilistic approach, and innovative evaluation framework to assess the performance of the proposed techniques. Experimental results are very encouraging w.r.t. state of the art. Additionally the method has revealed very robust against the various editorial formats of news programmes.

Keywords

audio-visual systems; information retrieval; multimedia systems; probability; audiovisual archives retrieval systems; broadcast news segmentation; innovative evaluation framework; probabilistic approach; probabilistic clusters; Audio databases; Broadcast technology; Broadcasting; Expert systems; Face detection; Feature extraction; Gunshot detection systems; Robustness; Speech; Technological innovation; broadcast news segmentation; shot clustering; user evaluation;

fLanguage

English

Publisher

ieee

Conference_Titel

Database and Expert Systems Application, 2008. DEXA '08. 19th International Workshop on

Conference_Location

Turin

ISSN

1529-4188

Print_ISBN

978-0-7695-3299-8

Type

conf

DOI

10.1109/DEXA.2008.65

Filename

4624783