Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Accurate Single-Stream Action Detection in Real-Time

Abstract : Analyzing videos of human actions involves understanding the spatial and temporal context of the scenes. State-of-the-art action detection approaches have demonstrated impressive results using Convolutional Neural Networks (CNNs) within a two-stream framework. However, most of them operate in a non-real-time, offline fashion, thus are not well-equipped in many emerging real-world scenarios such as autonomous driving and public surveillance. In addition, they are computationally demanding to be deployed on devices with limited power resources (e.g., embedded systems). To address the above challenges, we propose an efficient single-stream action detection framework by exploiting temporal coherence between successive video frames. This allows CNN appearance features to be cheaply propagated by motions rather than being extracted from every frame. Furthermore, we utilize an implicit motion representation to amplify appearance features. Our method based on motion-guided and motion-aware appearance features is evaluated on the UCF-101-24 dataset. Experiments indicate that the proposed method can achieve real-time action detection up to 32 fps with a comparable accuracy as the two-stream approach.
Liste complète des métadonnées

Littérature citée [28 références]  Voir  Masquer  Télécharger

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-02412443
Contributeur : Dominique Ginhac <>
Soumis le : dimanche 15 décembre 2019 - 14:18:15
Dernière modification le : jeudi 5 mars 2020 - 17:52:57
Document(s) archivé(s) le : lundi 16 mars 2020 - 13:25:56

Fichier

camera-ready-liu2019 (1).pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Yu Liu, Fan Yang, Dominique Ginhac. Accurate Single-Stream Action Detection in Real-Time. 13th International Conference on Distributed Smart Cameras (ICDSC 2019), Sep 2019, Trento, Italy. pp.1-6, ⟨10.1145/3349801.3349821⟩. ⟨hal-02412443⟩

Partager

Métriques

Consultations de la notice

106

Téléchargements de fichiers

153