Automatic segmentation of TV news into stories using visual and temporal information

Abstract : In this paper we propose a new method for automatic storyboard segmentation of TV news using image retrieval techniques and content manipulation. Our framework performs: shot boundary detection, global key-frame representation, image re-ranking based on neighborhood relations and temporal variance of image locations in order to construct a unimodal cluster for anchor person detection and differentiation. Finally, anchor shots are used to form video scenes. The entire technique is unsupervised being able to learn semantic models and extract natural patterns from the current video data. The experimental evaluation performed on a dataset of 50 videos, totalizing more than 30 hours, demonstrates the pertinence of the proposed method, with gains in terms of recall and precision rates with more than 5-7% when compared with state of the art techniques
Type de document :
Communication dans un congrès
ACIVS 2016 : 17th International Conference on Advanced Concepts for Intelligent Vision Systems, Oct 2016, Lecce, Italy. Springer, Proceedings ACIVS 2016 : 17th International Conference on Advanced Concepts for Intelligent Vision Systems, pp.648 - 660, 2016, <10.1007/978-3-319-48680-2_57>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01451798
Contributeur : Médiathèque Télécom Sudparis & Télécom Ecole de Management <>
Soumis le : mercredi 1 février 2017 - 14:27:01
Dernière modification le : jeudi 9 février 2017 - 16:13:12

Identifiants

Citation

Bogdan Mocanu, Ruxandra Tapu, Titus Zaharia. Automatic segmentation of TV news into stories using visual and temporal information. ACIVS 2016 : 17th International Conference on Advanced Concepts for Intelligent Vision Systems, Oct 2016, Lecce, Italy. Springer, Proceedings ACIVS 2016 : 17th International Conference on Advanced Concepts for Intelligent Vision Systems, pp.648 - 660, 2016, <10.1007/978-3-319-48680-2_57>. <hal-01451798>

Partager

Métriques

Consultations de la notice

57