Towards automatic understanding of narrative audiovisual content towards automatic understanding of narrative audiovisual content

Reboud, Alison
Thesis

Modern storytelling is digital and video-based. Understanding the stories contained in videos remains a challenge for automatic systems. Having multimodality as a transversal theme, this research thesis breaks down the "understanding" task into the following challenges: Predicting memorability, summarising and modelling stories from audiovisual content.


HAL
Type:
Thesis
Date:
2022-12-14
Department:
Data Science
Eurecom Ref:
7093
Copyright:
© EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in Thesis and is available at :
See also:

PERMALINK : https://www.eurecom.fr/publication/7093