Technicolor and INRIA/IRISA at MediaEval 2011: learning temporal modality integration with Bayesian Networks

Cédric Penet (1, 2) , Claire-Hélène Demarty (3) , Guillaume Gravier (2) , Patrick Gros (2)

1 Technicolor R & I [Cesson Sévigné]
2 TEXMEX - Multimedia content-based indexing
3 Technicolor [Cesson Sévigné]

This paper presents the work done in Technicolor and INRIA regarding the A ffect Task at MediaEval 2011. This task aims at detecting violent shots in movies. We studied a bayesian network framework, and several ways of introducing temporality and multimodality in the framework.

Domains: Machine Learning [cs.LG]

Cédric Penet, Claire-Hélène Demarty, Guillaume Gravier, Patrick Gros. Technicolor and INRIA/IRISA at MediaEval 2011: learning temporal modality integration with Bayesian Networks. MediaEval 2011, Multimedia Benchmark Workshop, Sep 2011, Pisa, Italy. ⟨hal-00643645⟩