Content-Based Video Description for Automatic Video Genre Categorization

Bogdan Ionescu (1) , Klaus Seyerlehner (2) , Christoph Rasche (1) , Constantin Vertan (1) , Patrick Lambert (3)

1 LAPI - Laboratorul de Analiza si Prelucrarea Imaginilor [Bucarest]
2 Department of Computational Perception
3 LISTIC - Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance

In this paper, we propose an audio-visual approach to video genre categorization. Audio information is extracted at block-level, which has the advantage of capturing local temporal information. At temporal structural level, we asses action contents with respect to human perception. Further, color perception is quantified with statistics of color distribution, elementary hues, color properties and relationship of color. The last category of descriptors determines statistics of contour geometry. An extensive evaluation of this multi-modal approach based on more than 91 hours of video footage is presented. We obtain average precision and recall ratios within [87% − 100%] and [77% − 100%], respectively,nwhile average correct classification is up to 97%. Additionally, movies displayed according to feature-based coordinates in a virtual 3D browsing environment tend to regroup with respect to genre, which has potential application with real content-based browsing systems.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Bogdan Ionescu, Klaus Seyerlehner, Christoph Rasche, Constantin Vertan, Patrick Lambert. Content-Based Video Description for Automatic Video Genre Categorization. 18th International Conference on Multimedia Modeling, Jan 2012, Austria. pp.51-62. ⟨hal-00732718⟩