Please use this identifier to cite or link to this item:
Title: Shot classification and keyframe detection for vision based speakers diarization in parliamentary debates
Authors: Marín Reyes, Pedro Antonio 
Lorenzo-Navarro, Javier 
Castrillón-Santana, Modesto 
Sánchez Nielsen, Elena
UNESCO Clasification: 120304 Inteligencia artificial
Keywords: Visual diarization
CNN classification
Biometric traits
Issue Date: 2016
Publisher: Springer 
Journal: Lecture Notes in Computer Science 
Conference: 17th Conference of the Spanish-Association-for-Artificial-Intelligence (CAEPIA 2016) 
17th Conference of the Spanish Association for Artificial Intelligence, (CAEPIA 2016) 
Abstract: Automatic labelling of speakers is an essential task for speakers diarization in parliamentary debates given the huge amount of video data to annotate. In this paper, we address the speaker diarization problem as a visual speaker re-identification issue with a special emphasis on the analysis of different shot types. We propose two approaches that makes use of convolutional neural networks (CNN) and biometric traits for keyframe extraction.
ISBN: 978-3-319-44635-6
ISSN: 0302-9743
DOI: 10.1007/978-3-319-44636-3_5
Source: Advances in Artificial Intelligence. CAEPIA 2016. Lecture Notes in Computer Science, v. 9868 LNCS, p. 48-57
Appears in Collections:Capítulo de libro
Adobe PDF (9 MB)
Show full item record

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.