Automatic extraction of story units from TV news - Archive ouverte HAL
Communication Dans Un Congrès Année : 2017

Automatic extraction of story units from TV news

Résumé

In this paper we propose a novel method for automatic identification of semantically consistent story units from TV news programs. The method includes a temporal segmentation procedure of the video based on visual cues, as well as a graph-driven textual analysis technique of the subtitles documents. The experimental results, obtained on a dataset of 50 videos selected from one week video archive of France Television demonstrate the pertinence of the proposed approach
Fichier non déposé

Dates et versions

hal-01511894 , version 1 (21-04-2017)

Identifiants

Citer

Bogdan Mocanu, Ruxandra Tapu, Titus Zaharia. Automatic extraction of story units from TV news. ICCE 2017 : International Conference on Consumer Electronics, Jan 2017, Las Vegas United States. pp.1 - 2, ⟨10.1109/ICCE.2017.7889377⟩. ⟨hal-01511894⟩
93 Consultations
0 Téléchargements

Altmetric

Partager

More