Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Fazliddin Anvarov"'
Publikováno v:
IEEE Access, Vol 9, Pp 39218-39228 (2021)
Conventional approaches for video action recognition were designed to learn feature maps using 3D convolutional neural networks (CNNs). For better action recognition, they trained the large-scale video datasets with the representation power of 3D CNN
Externí odkaz:
https://doaj.org/article/50e357709f74437d8d776588c8b16207
Publikováno v:
Electronics
Volume 9
Issue 1
Electronics, Vol 9, Iss 1, p 147 (2020)
Volume 9
Issue 1
Electronics, Vol 9, Iss 1, p 147 (2020)
Action recognition is an active research field that aims to recognize human actions and intentions from a series of observations of human behavior and the environment. Unlike image-based action recognition mainly using a two-dimensional (2D) convolut