Scene Linking Annotation and Automatic Scene Characterization in TV Series - Université Paris-Saclay Access content directly
Journal Articles CEUR Workshop Proceedings Year : 2021

Scene Linking Annotation and Automatic Scene Characterization in TV Series

Camille Guinaudeau
  • Function : Author
  • PersonId : 1106315
Claude Barras
  • Function : Author
  • PersonId : 1208716

Abstract

In the context of a large collection of multimedia documents, creating links between documents or scenes can help to organize the collection. For TV series, this organization can be achieved by means of narrative structure extraction through scene linking. Narrative characteristics such as speaking characters, entity mentions and theme can be used to characterize scenes. The linking of scenes can be between scenes inside an episode, between scenes in di↵erent episodes and/or in di↵erent seasons, since stories in TV series progress at di↵erent level of granularity. In this work, we have annotated the links between the scenes of the first two seasons of the TV series Game of Thrones, using predefined stories and sub stories. We have also automatically extracted the narrative characteristics of each scene. The dataset is composed by 444 scenes, involving 154 speaking character organized in 46 stories divided into 151 sub stories and 5 sub sub-stories.
Fichier principal
Vignette du fichier
paper6[1].pdf (510.42 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03907934 , version 1 (20-12-2022)

Licence

Copyright

Identifiers

  • HAL Id : hal-03907934 , version 1

Cite

Aman Berhe, Camille Guinaudeau, Claude Barras. Scene Linking Annotation and Automatic Scene Characterization in TV Series. CEUR Workshop Proceedings, 2021. ⟨hal-03907934⟩
15 View
30 Download

Share

Gmail Facebook X LinkedIn More