Cargando…
A Bayesian Dynamical Approach for Human Action Recognition
We introduce a generative Bayesian switching dynamical model for action recognition in 3D skeletal data. Our model encodes highly correlated skeletal data into a few sets of low-dimensional switching temporal processes and from there decodes to the motion data and their associated action labels. We...
Autores principales: | Farnoosh, Amirreza, Wang, Zhouping, Zhu, Shaotong, Ostadabbas, Sarah |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8402468/ https://www.ncbi.nlm.nih.gov/pubmed/34451054 http://dx.doi.org/10.3390/s21165613 |
Ejemplares similares
-
Target-Specific Action Classification for Automated Assessment of Human Motor Behavior from Video
por: Rezaei, Behnaz, et al.
Publicado: (2019) -
An Efficient Bayesian Approach to Exploit the Context of Object-Action Interaction for Object Recognition
por: Yoon, Sungbaek, et al.
Publicado: (2016) -
A Hierarchical Learning Approach for Human Action Recognition
por: Lemieux, Nicolas, et al.
Publicado: (2020) -
Bayesian Action–Perception Computational Model: Interaction of Production and Recognition of Cursive Letters
por: Gilet, Estelle, et al.
Publicado: (2011) -
Jointly Learning Multiple Sequential Dynamics for Human Action Recognition
por: Liu, An-An, et al.
Publicado: (2015)