Titre :

Human Motion Prediction Using Manifold-Aware Wasserstein GAN

Auteur(s) :

Chopin, Baptiste [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Otberdout, Naima [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Daoudi, Mohamed [Auteur]
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Nord Europe]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Bartolo, Angela [Auteur]
Laboratoire Sciences Cognitives et Sciences Affectives - UMR 9193 [SCALab]

Titre de la manifestation scientifique :

IEEE conference series on Automatic Face and Gesture Recognition

Ville :

Jodhpur (virtual)

Pays :

Inde

Date de début de la manifestation scientifique :

2021-12-15

Discipline(s) HAL :

Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]

Résumé en anglais : [en]

Human motion prediction aims to forecast future human poses given a prior pose sequence. The discontinuity of the predicted motion and the performance deterioration in long-term horizons are still the main challenges ...
Lire la suite >Human motion prediction aims to forecast future human poses given a prior pose sequence. The discontinuity of the predicted motion and the performance deterioration in long-term horizons are still the main challenges encountered in current literature. In this work, we tackle these issues by using a compact manifold-valued representation of human motion. Specifically, we model the temporal evolution of the 3D human poses as trajectory, what allows us to map human motions to single points on a sphere manifold. To learn these non-Euclidean representations, we build a manifold-aware Wasserstein generative adversarial model that captures the temporal and spatial dependencies of human motion through different losses. Extensive experiments show that our approach outperforms the state-of-the-art on CMU MoCap and Human 3.6M datasets. Our qualitative results show the smoothness of the predicted motions. The pretrained models and the code are provided at the following link.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet ANR :

ULNE

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL