Mengmeng Yan1, Chuang Zhang1,2,*, Jinqi Chu1, Haichao Zhang1, Tao Ge1, Suting Chen1
Computer Systems Science and Engineering, Vol.47, No.2, pp. 1433-1449, 2023, DOI:10.32604/csse.2023.040132
Abstract An action recognition network that combines multi-level spatiotemporal feature fusion with an attention mechanism is proposed as a solution to the issues of single spatiotemporal feature scale extraction, information redundancy, and insufficient extraction of frequency domain information in channels in 3D convolutional neural networks. Firstly, based on 3D CNN, this paper designs a new multilevel spatiotemporal feature fusion (MSF) structure, which is embedded in the network model, mainly through multilevel spatiotemporal feature separation, splicing and fusion, to achieve the fusion of spatial perceptual fields and short-medium-long time series information at different scales with reduced network parameters; In the second step,… More >
Login
Register
