I3D-Shufflenet Based Human Action Recognition
In view of difficulty in application of optical flow based human action recognition due to large amount of calculation, a human action recognition algorithm I3D-shufflenet model is proposed combining the advantages of I3D neural network and lightweight model shufflenet. The 5 × 5 convolution kernel...
Main Authors: | Guocheng Liu, Caixia Zhang, Qingyang Xu, Ruoshi Cheng, Yong Song, Xianfeng Yuan, Jie Sun |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Algorithms |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-4893/13/11/301 |
Similar Items
-
AR3D: Attention Residual 3D Network for Human Action Recognition
by: Min Dong, et al.
Published: (2021-02-01) -
Chinese Lip-Reading Research Based on ShuffleNet and CBAM
by: Yixian Fu, et al.
Published: (2023-01-01) -
An Effective WBC Segmentation and Classification Using MobilenetV3–ShufflenetV2 Based Deep Learning Framework
by: Bairaboina Sai Sambasiva Rao, et al.
Published: (2023-01-01) -
LA-ShuffleNet: A Strong Convolutional Neural Network for Edge Computing Devices
by: Hui Zhang, et al.
Published: (2023-01-01) -
A 3D graph convolutional networks model for 2D skeleton‐based human action recognition
by: Libo Weng, et al.
Published: (2023-02-01)