Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition - Interactions, Réalité Augmentée, Robotique Ambiante Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2021

Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition

Apprentissage profond multi-tâche pour l'estimation de pause humaine 3D et la reconnaissance d'action en temps réel

Résumé

Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis. Nonetheless, most recent methods in the literature handle the two problems separately. In this work, we propose a multi-task framework for jointly estimating 2D or 3D human poses from monocular color images and classifying human actions from video sequences. We show that a single architecture can be used to solve both problems in an efficient way and still achieves state-of-the-art or comparable results at each task while running with a throughput of more than 100 frames per second. The proposed method benefits from high parameters sharing between the two tasks by unifying still images and video clips processing in a single pipeline, allowing the model to be trained with data from different categories simultaneously and in a seamlessly way. Additionally, we provide important insights for end-to-end training the proposed multi-task model by decoupling key prediction parts, which consistently leads to better accuracy on both tasks. The reported results on four datasets (MPII, Human3.6M, Penn Action and NTU RGB+D) demonstrate the effectiveness of our method on the targeted tasks. Our source code and trained weights are publicly available at https://github.com/dluvizon/deephar.
Fichier principal
Vignette du fichier
tpami19_multitask.pdf (3.56 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02558843 , version 1 (29-04-2020)

Identifiants

Citer

Diogo C Luvizon, David Picard, Hedi Tabia. Multi-task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43 (8), pp.2752--2764. ⟨10.1109/TPAMI.2020.2976014⟩. ⟨hal-02558843⟩
305 Consultations
135 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More