· · · Conference Proceedings hosted by TU Delft Library

Home · About · Disclaimer ·

Segmentation TV series into scenes using speaker diarization


Author: Ercolessi, P. · Sénac, C. · Joly, P. · Bredin, H.
Type:Conference paper
Publisher/Organization: TU Delft; EWI; MM; PRB
Source:WIAMIS 2011: 12th International Workshop on Image Analysis for Multimedia Interactive Services, Delft, The Netherlands, April 13-15, 2011
ISBN: 978-94-90818-00-5
Rights: (c) 2011 Ercolessi, P.; Sénac, C.; Joly, P.; Bredin, H.


In this paper, we propose a novel approach to perform scene segmentation of TV series. Using the output of our existing speaker diarization system, any temporal segment of the video can be described as a binary feature vector. A straightforward segmentation algorithm then allows to group similar contiguous speaker segments into scenes. An additional visual-only color-based segmentation is then used to refine the first segmentation. Experiments are performed on a subset of the Ally McBeal TV series and show promising results, obtained with a rule-free and genericmethod. For comparison purposes, test corpus annotations and description are made available to the community.

Content Viewer