Action Classification in Soccer Videos with Long Short-Term Memory Recurrent Neural Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

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

Franck Mamalet
Christophe Garcia

Résumé

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 %.

Dates et versions

hal-01381827 , version 1 (14-10-2016)

Identifiants

Citer

Moez Baccouche, Franck Mamalet, Christian Wolf, Christophe Garcia, Atilla Baskurt. Action Classification in Soccer Videos with Long Short-Term Memory Recurrent Neural Networks. 20th International Conference on Artificial Neural Networks (ICANN), Sep 2010, Thessaloniki, Greece. pp.154-159, ⟨10.1007/978-3-642-15822-3_20⟩. ⟨hal-01381827⟩
416 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More