Beat-Event Detection in Action Movie Franchises

Danila Potapov 1 Matthijs Douze 1, 2 Jerome Revaud 1 Zaid Harchaoui 1, 3 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : While important advances were recently made towards temporally localizing and recognizing specific human actions or activities in videos, efficient detection and classification of long video chunks belonging to semantically defined categories such as “pursuit” or “romance” remains challenging. We introduce a new dataset, Action Movie Franchises, consisting of a collection of Hollywood action movie franchises. We define 11 non-exclusive semantic categories — called beat-categories — that are broad enough to cover most of the movie footage. The corresponding beat-events are annotated as groups of video shots, possibly overlapping. We propose an approach for localizing beat-events based on classifying shots into beat-categories and learning the temporal constraints between shots. We show that temporal constraints significantly improve the classification performance. We set up an evaluation protocol for beat-event localization as well as for shot classification, depending on whether movies from the same franchise are present or not in the training data.
Type de document :
Pré-publication, Document de travail
Liste complète des métadonnées
Contributeur : Thoth Team <>
Soumis le : vendredi 14 août 2015 - 16:53:01
Dernière modification le : mardi 13 novembre 2018 - 15:50:27
Document(s) archivé(s) le : dimanche 15 novembre 2015 - 10:50:50


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01183588, version 1
  • ARXIV : 1508.03755



Danila Potapov, Matthijs Douze, Jerome Revaud, Zaid Harchaoui, Cordelia Schmid. Beat-Event Detection in Action Movie Franchises. 2015. 〈hal-01183588〉



Consultations de la notice


Téléchargements de fichiers