LIG at MediaEval 2015 Multimodal Person Discovery in Broadcast TV Task

Mateusz Budnik (1) , Bahjat Safadi (1) , Laurent Besacier (2, 3) , Georges Quénot (1) , Ali Khodabakhsh (1) , Cenk Demiroglu (4)

1 LIG - Laboratoire d'Informatique de Grenoble
2 GETALP - Groupe d’Étude en Traduction Automatique/Traitement Automatisé des Langues et de la Parole
3 IUF - Institut universitaire de France
4 Istanbul University

In this working notes paper the contribution of the LIG team (partnership between Univ. Grenoble Alpes and Ozyegin University) to the Multimodal Person Discovery in Broadcast TV task in MediaEval 2015 is presented. The task focused on unsupervised learning techniques. Two different approaches were submitted by the team. In the first one, new features for face and speech modalities were tested. The second method presents an alternative way to calculate the distance between face tracks and speech segments. It also had a competitive MAP score and was able to beat the baseline.

Domaines: Informatique et langage [cs.CL]

Mateusz Budnik, Bahjat Safadi, Laurent Besacier, Georges Quénot, Ali Khodabakhsh, et al.. LIG at MediaEval 2015 Multimodal Person Discovery in Broadcast TV Task. MediaEval 2015 Workshop, Sep 2015, Wurzen, Germany. ⟨hal-01350079⟩