Multimodal Violence Detection in Hollywood Movies: State-of-the-Art and Benchmarking

Abstract : This chapter introduces a benchmark evaluation targeting the detection of violent scenes in Hollywood movies. The evaluation was implemented in 2011 and 2012 as an affect task in the framework of the international MediaEval benchmark initiative. We report on these 2 years of evaluation, providing a detailed description of the dataset created, describing the state of the art by studying the results achieved by participants and providing a detailed analysis of two of the best performing multimodal systems. We elaborate on the lessons learned after 2 years to provide insights on future work emphasizing multimodal modeling and fusion.
Type de document :
Chapitre d'ouvrage
Ionescu, Bogdan and Benois-Pineau, Jenny and Piatrik, Tomas and Quénot, Georges. Fusion in Computer Vision, Springer International Publishing, pp.185-208, 2014, Advances in Computer Vision and Pattern Recognition, 〈10.1007/978-3-319-05696-8_8〉
Liste complète des métadonnées

https://hal.inria.fr/hal-00968515
Contributeur : Cédric Penet <>
Soumis le : mardi 1 avril 2014 - 10:21:26
Dernière modification le : vendredi 16 novembre 2018 - 01:23:13

Identifiants

Citation

Claire-Hélène Demarty, Cédric Penet, Bogdan Ionescu, Guillaume Gravier, Mohammad Soleymani. Multimodal Violence Detection in Hollywood Movies: State-of-the-Art and Benchmarking. Ionescu, Bogdan and Benois-Pineau, Jenny and Piatrik, Tomas and Quénot, Georges. Fusion in Computer Vision, Springer International Publishing, pp.185-208, 2014, Advances in Computer Vision and Pattern Recognition, 〈10.1007/978-3-319-05696-8_8〉. 〈hal-00968515〉

Partager

Métriques

Consultations de la notice

949