Focused Attention for Action Recognition - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Focused Attention for Action Recognition

Résumé

Current state-of-the art approaches to action recognition emphasize learning ConvNets on large amounts of training data, using 3D convolutions to process the temporal dimension. This approach is expensive in terms of memory usage and constitutes a major performance bottleneck of existing approaches. Further, video input data points typically include irrelevant information, along with useful features, which limits the level of detail that networks can process, regardless of the quality of the original video. Hence, models that can focus computational resources on relevant training signal are desirable.To address this problem, we rely on network-specific saliency outputs to drive an attention model that provides tighter crops around relevant video regions. We experimentally validate this approach and show how this strategy improves performance for the action recognition task.
Fichier principal
Vignette du fichier
paper.pdf (224.53 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02292339 , version 1 (19-09-2019)

Identifiants

  • HAL Id : hal-02292339 , version 1

Citer

Vladyslav Sydorov, Karteek Alahari, Cordelia Schmid. Focused Attention for Action Recognition. BMVC 2019 - British Machine Vision Conference, Sep 2019, Cardiff, United Kingdom. pp.1-13. ⟨hal-02292339⟩
660 Consultations
615 Téléchargements

Partager

Gmail Facebook X LinkedIn More