[en] In this paper, we present the work done at UMons regarding
the MediaEval 2015 Affective Impact of Movies Task
(including Violent Scenes Detection). This task can be divided
into two subtasks. On the one hand, Violent Scene
Detection, which means automatically finding scenes that
are violent in a set if videos. And on the other hand, evaluate
the affective impact of the video, through an estimation
of the valence and arousal. In order to offer a solution for
both detection and classification subtasks, we investigate different
visual and auditory feature extraction methods. An
i-vector approach is applied for the audio, and optical
flow maps processed through a deep convolutional neural network
are tested for extracting features from the video. Classifiers
based on probabilistic linear discriminant analysis and fully
connected feed-forward neural networks are then used.
Research center :
CRTI - Centre de Recherche en Technologie de l'Information
Disciplines :
Library & information sciences
Author, co-author :
Seddati, Omar ; Université de Mons > Faculté Polytechnique > Information, Signal et Intelligence artificielle
Emre, Kulah
Pironkov, Gueorgui ; Université de Mons > Faculté Polytechnique > Information, Signal et Intelligence artificielle
Dupont, Stéphane ; Université de Mons > Faculté Polytechnique > Information, Signal et Intelligence artificielle
Mahmoudi, Said ; Université de Mons > Faculté Polytechnique > Informatique, Logiciel et Intelligence artificielle
Dutoit, Thierry ; Université de Mons > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Language :
English
Title :
UMons at MediaEval 2015 Affective Impact of Movies Task including Violent Scenes Detection
Publication date :
14 September 2015
Journal title :
IEEE Multimedia
ISSN :
1070-986X
Publisher :
Institute of Electrical and Electronics Engineers, United States
Peer reviewed :
Peer Reviewed verified by ORBi
Research unit :
F105 - Information, Signal et Intelligence artificielle
Research institute :
R300 - Institut de Recherche en Technologies de l'Information et Sciences de l'Informatique R450 - Institut NUMEDIART pour les Technologies des Arts Numériques