Cargando…
Self-organizing neural integration of pose-motion features for human action recognition
The visual recognition of complex, articulated human movements is fundamental for a wide range of artificial systems oriented toward human-robot communication, action classification, and action-driven perception. These challenging tasks may generally involve the processing of a huge amount of visual...
Autores principales: | Parisi, German I., Weber, Cornelius, Wermter, Stefan |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2015
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4460528/ https://www.ncbi.nlm.nih.gov/pubmed/26106323 http://dx.doi.org/10.3389/fnbot.2015.00003 |
Ejemplares similares
-
Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization
por: Parisi, German I., et al.
Publicado: (2018) -
Compositional Learning of Human Activities With a Self-Organizing Neural Architecture
por: Mici, Luiza, et al.
Publicado: (2019) -
Toward a self-organizing pre-symbolic neural model representing sensorimotor primitives
por: Zhong, Junpei, et al.
Publicado: (2014) -
Learning indoor robot navigation using visual and sensorimotor map information
por: Yan, Wenjie, et al.
Publicado: (2013) -
Spatial relation learning in complementary scenarios with deep neural networks
por: Lee, Jae Hee, et al.
Publicado: (2022)