Yang Wu1, Lei Guo1, Xiaodong Dai1, Bin Zhang1, Dong-Won Park2, Ming Ma1,*
CMC-Computers, Materials & Continua, Vol.73, No.3, pp. 5911-5924, 2022, DOI:10.32604/cmc.2022.031664
Abstract Action recognition has become a current research hotspot in computer vision. Compared to other deep learning methods, Two-stream convolutional network structure achieves better performance in action recognition, which divides the network into spatial and temporal streams, using video frame images as well as dense optical streams in the network, respectively, to obtain the category labels. However, the two-stream network has some drawbacks, i.e., using dense optical flow as the input of the temporal stream, which is computationally expensive and extremely time-consuming for the current extraction algorithm and cannot meet the requirements of real-time tasks. In this paper, instead of the… More >
Login
Register
