TRACK: A Multi-Modal Deep Architecture for Head Motion Prediction in 360-Degree Videos - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

TRACK: A Multi-Modal Deep Architecture for Head Motion Prediction in 360-Degree Videos

Résumé

Head motion prediction is an important problem with 360 • videos, in particular to inform the streaming decisions. Various methods tackling this problem with deep neural networks have been proposed recently. In this article, we introduce a new deep architecture, named TRACK, that benefits both from the history of past positions and knowledge of the video content. We show that TRACK achieves state-of-the-art performance when compared against all recent approaches considering the same datasets and wider prediction horizons: from 0 to 5 seconds.
Fichier principal
Vignette du fichier
ICIP2020_accepted.pdf (275.48 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02615980 , version 1 (23-07-2020)

Identifiants

  • HAL Id : hal-02615980 , version 1

Citer

Miguel Fabian Romero Rondon, Lucile Sassatelli, Ramon Aparicio-Pardo, Frédéric Precioso. TRACK: A Multi-Modal Deep Architecture for Head Motion Prediction in 360-Degree Videos. ICIP 2020 - IEEE International Conference on Image Processing, Oct 2020, Abu Dhabi / Virtual, United Arab Emirates. ⟨hal-02615980⟩
154 Consultations
181 Téléchargements

Partager

Gmail Facebook X LinkedIn More