A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from RGB sensors using simple cameras. The approach proceeds along two stages. In the first, a real-time 2D pose detector is run to determine the precise pixel location of important keypoin...

Descripción completa

Detalles Bibliográficos
Autores principales: Pham, Huy Hieu, Salmane, Houssam, Khoudour, Louahdi, Crouzil, Alain, Velastin, Sergio A., Zegers, Pablo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7180926/
https://www.ncbi.nlm.nih.gov/pubmed/32218350
http://dx.doi.org/10.3390/s20071825

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7180926/
https://www.ncbi.nlm.nih.gov/pubmed/32218350
http://dx.doi.org/10.3390/s20071825

Ejemplares similares