Beat-Event Detection in Action Movie Franchises - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2015

Beat-Event Detection in Action Movie Franchises

Résumé

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.
Fichier principal
Vignette du fichier
actionmovies.pdf (1.61 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01183588 , version 1 (14-08-2015)

Identifiants

Citer

Danila Potapov, Matthijs Douze, Jerome Revaud, Zaid Harchaoui, Cordelia Schmid. Beat-Event Detection in Action Movie Franchises. 2015. ⟨hal-01183588⟩
514 Consultations
810 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More