Human Motion Prediction Using Manifold-Aware ...
Type de document :
Communication dans un congrès avec actes
URL permanente :
Titre :
Human Motion Prediction Using Manifold-Aware Wasserstein GAN
Auteur(s) :
Chopin, Baptiste [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Otberdout, Naima [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Daoudi, Mohamed [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Bartolo, Angela [Auteur]
Sciences Cognitives et Sciences Affectives (SCALab) - UMR 9193
Chopin, Baptiste [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Otberdout, Naima [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Daoudi, Mohamed [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Ecole nationale supérieure Mines-Télécom Lille Douai [IMT Lille Douai]
Bartolo, Angela [Auteur]
Sciences Cognitives et Sciences Affectives (SCALab) - UMR 9193
Chopin, Baptiste [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Titre de la manifestation scientifique :
2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)
Ville :
Jodhpur
Pays :
Inde
Date de début de la manifestation scientifique :
2021-12-15
Éditeur :
IEEE
Date de publication :
2021-12-15
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 >
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
Établissement(s) :
Université de Lille
CNRS
CHU Lille
CNRS
CHU Lille
Équipe(s) de recherche :
Équipe Action, Vision et Apprentissage (AVA)
Date de dépôt :
2024-01-04T08:16:12Z
2024-01-10T17:29:05Z
2024-01-10T17:29:05Z
Fichiers
- document
- Accès libre
- Human Motion Prediction Using Manifold-Aware Wasserstein GAN
- Accéder au document