Action Classification in Soccer Videos with Long Short-Term Memory Recurrent Neural Networks

Moez Baccouche 1 Franck Mamalet Christian Wolf 1 Christophe Garcia Atilla Baskurt 1
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : In this paper, we propose a novel approach for action classification in soccer videos using a recurrent neural network scheme. Thereby, we extract from each video action at each timestep a set of features which describe both the visual content (by the mean of a BoW approach) and the dominant motion (with a key point based approach). A Long Short-Term Memory-based Recurrent Neural Network is then trained to classify each video sequence considering the temporal evolution of the features for each timestep. Experimental results on the MICC-Soccer-Actions-4 database show that the proposed approach outperforms classification methods of related works (with a classification rate of 77 %), and that the combination of the two features (BoW and dominant motion) leads to a classification rate of 92 %.
Type de document :
Communication dans un congrès
K. Diamantaras, W. Duch, L.S. Iliadis. 20th International Conference on Artificial Neural Networks (ICANN), Sep 2010, Thessaloniki, Greece. Springer, pp.154-159, 2010, 〈10.1007/978-3-642-15822-3_20〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01381827
Contributeur : Équipe Gestionnaire Des Publications Si Liris <>
Soumis le : vendredi 14 octobre 2016 - 17:57:14
Dernière modification le : jeudi 19 avril 2018 - 14:38:06

Lien texte intégral

Identifiants

Citation

Moez Baccouche, Franck Mamalet, Christian Wolf, Christophe Garcia, Atilla Baskurt. Action Classification in Soccer Videos with Long Short-Term Memory Recurrent Neural Networks. K. Diamantaras, W. Duch, L.S. Iliadis. 20th International Conference on Artificial Neural Networks (ICANN), Sep 2010, Thessaloniki, Greece. Springer, pp.154-159, 2010, 〈10.1007/978-3-642-15822-3_20〉. 〈hal-01381827〉

Partager

Métriques

Consultations de la notice

216