Efficient neural models for visual attention - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Efficient neural models for visual attention

Résumé

Human vision rely on attention to select only a few regions to process and thus reduce the complexity and the processing time of visual task. Artificial vision systems can benefit from a bio-inspired attentional process relying on neural models. In such applications, what is the most efficient neural model: spiked-based or frequency-based? We propose an evaluation of both neural model, in term of complexity and quality of results (on artificial and natural images).
Fichier principal
Vignette du fichier
Spikefreq-CameraReady.pdf (95.63 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00529523 , version 1 (25-10-2011)

Identifiants

Citer

Sylvain Chevallier, Nicolas Cuperlier, Philippe Gaussier. Efficient neural models for visual attention. Computer Vision and Graphics, Sep 2010, Varsovie, Poland. pp.257-264, ⟨10.1007/978-3-642-15910-7⟩. ⟨hal-00529523⟩
187 Consultations
242 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More