@inproceedings{d3050cbe97ec47c98e4af2327035ae6c,
title = "Fusion of speech, faces and text for person identification in TV broadcast",
abstract = "The Repere challenge is a project aiming at the evaluation of systems for supervised and unsupervised multimodal recognition of people in TV broadcast. In this paper, we describe, evaluate and discuss QCompere consortium submissions to the 2012 Repere evaluation campaign dry-run. Speaker identification (and face recognition) can be greatly improved when combined with name detection through video optical character recognition. Moreover, we show that unsupervised multimodal person recognition systems can achieve performance nearly as good as supervised monomodal ones (with several hundreds of identity models).",
author = "Herv{\'e} Bredin and Johann Poignant and Makarand Tapaswi and Guillaume Fortier and Le, \{Viet Bac\} and Thibault Napoleon and Hua Gao and Claude Barras and Sophie Rosset and Laurent Besacier and Jakob Verbeek and Georges Qu{\'e}not and Fr{\'e}d{\'e}ric Jurie and Ekenel, \{Hazim Kemal\}",
year = "2012",
doi = "10.1007/978-3-642-33885-4\_39",
language = "English",
isbn = "9783642338847",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
number = "PART 3",
pages = "385--394",
booktitle = "Computer Vision, ECCV 2012 - Workshops and Demonstrations, Proceedings",
address = "Germany",
edition = "PART 3",
note = "Computer Vision, ECCV 2012 - Workshops and Demonstrations, Proceedings ; Conference date: 07-10-2012 Through 13-10-2012",
}