3D network with channel excitation and knowledge distillation for action recognition

Modern action recognition techniques frequently employ two networks: the spatial stream, which accepts input from RGB frames, and the temporal stream, which accepts input from optical flow. Recent researches use 3D convolutional neural networks that employ spatiotemporal filters on both streams. Alt...

Descripción completa

Detalles Bibliográficos
Autores principales: Hu, Zhengping, Mao, Jianzeng, Yao, Jianxin, Bi, Shuai
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Neuroscience
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10076829/
https://www.ncbi.nlm.nih.gov/pubmed/37033413
http://dx.doi.org/10.3389/fnbot.2023.1050167

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10076829/
https://www.ncbi.nlm.nih.gov/pubmed/37033413
http://dx.doi.org/10.3389/fnbot.2023.1050167

Ejemplares similares