COARSE-TO-FINE AGGREGATION FOR CROSS-GRANULARITY ACTION RECOGNITION - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

COARSE-TO-FINE AGGREGATION FOR CROSS-GRANULARITY ACTION RECOGNITION

Ahmed Mazari
  • Fonction : Auteur
Hichem Sahbi

Résumé

In this paper, we introduce a novel hierarchical aggregation design that captures different levels of temporal granularity in action recognition. Our design principle is coarse-to-fine and achieved using a tree-structured network; as we traverse this network top-down, pooling operations are getting less invariant but timely more resolute and well localized. Learning the combination of operations in this network-which best fits a given ground-truth-is obtained by solving a constrained minimization problem whose solution corresponds to the distribution of weights that capture the contribution of each level (and thereby temporal granularity) in the global hierarchical pooling process. Besides being principled and well grounded, the proposed hierarchical pooling is also video-length agnostic and resilient to misalignments in actions. Extensive experiments conducted on the challenging UCF-101 database corroborate these statements.
Fichier principal
Vignette du fichier
paperICIP2020b.pdf (323.9 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03089394 , version 1 (28-12-2020)

Identifiants

  • HAL Id : hal-03089394 , version 1

Citer

Ahmed Mazari, Hichem Sahbi. COARSE-TO-FINE AGGREGATION FOR CROSS-GRANULARITY ACTION RECOGNITION. IEEE ICIP, 2020, Abu-Dhabi, United Arab Emirates. ⟨hal-03089394⟩

Collections

CNRS
21 Consultations
106 Téléchargements

Partager

Gmail Facebook X LinkedIn More