A Spatio-Temporal Motion Network for Action Recognition Based on Spatial Attention

Temporal modeling is the key for action recognition in videos, but traditional 2D CNNs do not capture temporal relationships well. 3D CNNs can achieve good performance, but are computationally intensive and not well practiced on existing devices. Based on these problems, we design a generic and effe...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Qi, Lu, Tongwei, Zhou, Huabing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947561/
https://www.ncbi.nlm.nih.gov/pubmed/35327879
http://dx.doi.org/10.3390/e24030368

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947561/
https://www.ncbi.nlm.nih.gov/pubmed/35327879
http://dx.doi.org/10.3390/e24030368

Ejemplares similares