PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Fusion of speech, faces and text for person identification in TV broadcast
H. Bredin, J. Poignant, M. Tapaswi, G. Fortier, V.-B. Le, T. Napoléon, G. Hua, C. Barras, S. Rosset, L. Besacier, Jakob Verbeek, G. Quenot, Frederic Jurie and E.-H. Kemal
In: ECCV Workshop on Information fusion in Computer Vision for Concept Recognition(2012).

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).

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Speech
Multimodal Integration
ID Code:9603
Deposited By:Jakob Verbeek
Deposited On:01 December 2012