A framework for dialogue detection in movies
File(s)
Accepted version
Author(s)
Kotti, Margarita
Kotropoulos, Constantine
Ziòlko, Bartosz
Pitas, Ioannis
Moschou, Vassiliki
Type
Conference Paper
Abstract
In this paper, we investigate a novel framework for dialogue detection that is based on indicator functions. An indicator function defines that a particular actor is present at each time instant. Two dialogue detection rules are developed and assessed. The first rule relies on the value of the cross-correlation function at zero time lag that is compared to a threshold. The second rule is based on the cross-power in a particular frequency band that is also compared to a threshold. Experiments are carried out in order to validate the feasibility of the aforementioned dialogue detection rules by using ground-truth indicator functions determined by human observers from six different movies. A total of 25 dialogue scenes and another 8 non-dialogue scenes are employed. The probabilities of false alarm and detection are estimated by cross-validation, where 70% of the available scenes are used to learn the thresholds employed in the dialogue detection rules and the remaining 30% of the scenes are used for testing. An almost perfect dialogue detection is reported for every distinct threshold. © Springer-Verlag Berlin Heidelberg 2006.
Date Issued
2006-09
Citation
Multimedia Content Representation, Classification, and Security, 2006, pp.371-378
ISBN
978-3-540-39392-4
Publisher
Springer
Start Page
371
End Page
378
Journal / Book Title
Multimedia Content Representation, Classification, and Security
Copyright Statement
© 2006 Springer-Verlag Berlin Heidelberg. The original publication is available at www.springerlink.com
Description
14.11.13 KB. Ok to add accepted version to spiral, embargo period elapsed.
Source
International Workshop, MRCS 2006
Source Place
Instanbul, Turkey
Start Date
2006-09-11
Finish Date
2006-09-13
Coverage Spatial
Istanbul, Turkey