Print Email Facebook Twitter Segmentation TV series into scenes using speaker diarization Part of: WIAMIS 2011: 12th International Workshop on Image Analysis for Multimedia Interactive Services· list the conference papers Title Segmentation TV series into scenes using speaker diarization Author Ercolessi, P. Sénac, C. Joly, P. Bredin, H. Date 2011-04-13 Abstract 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. To reference this document use: http://resolver.tudelft.nl/uuid:71be2da9-4a17-409a-9c6c-ee3f59ac71cf Part of collection Conference proceedings Document type conference paper Rights (c) 2011 Ercolessi, P.; Sénac, C.; Joly, P.; Bredin, H. Files PDF 34.pdf 438.08 KB Close viewer /islandora/object/uuid:71be2da9-4a17-409a-9c6c-ee3f59ac71cf/datastream/OBJ/view