EUMSSI team at the MediaEval Person Discovery Challenge - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

EUMSSI team at the MediaEval Person Discovery Challenge

Abstract

We present the results of the EUMSSI team's participation in the Multimodal Person Discovery task at the MediaEval challenge 2015. The goal is to identify all people who simultaneously appear and speak in a video corpus, which implicitly involves both audio stream and visual stream. We emphasize on improving each modality separately and bench-marking them to analyze their pros and cons.
Fichier principal
Vignette du fichier
Paper71.pdf (178.95 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01433209 , version 1 (01-04-2017)

Identifiers

  • HAL Id : hal-01433209 , version 1

Cite

Nam Le, Di Wu, Sylvain Meignier, Jean-Marc Odobez. EUMSSI team at the MediaEval Person Discovery Challenge. MediaEval 2015 , 2015, Wurzen, Germany. ⟨hal-01433209⟩
88 View
23 Download

Share

Gmail Facebook Twitter LinkedIn More