RGB-D Human Action Recognition of Deep Feature Enhancement and Fusion Using Two-Stream ConvNet
Action recognition is an important research direction of computer vision, whose performance based on video images is easily affected by factors such as background and light, while deep video images can better reduce interference and improve recognition accuracy. Therefore, this paper makes full use...
Main Authors: | Yun Liu, Ruidi Ma, Hui Li, Chuanxu Wang, Ye Tao |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2021-01-01
|
Series: | Journal of Sensors |
Online Access: | http://dx.doi.org/10.1155/2021/8864870 |
Similar Items
-
Classification of Multivariate Time Series through Transformation into RGB Images for ConvNet
by: Zhi-Xuan Chen, et al.
Published: (2019) -
FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets
by: Abu Quwsar Ohi, et al.
Published: (2021-01-01) -
Blended Multi-Modal Deep ConvNet Features for Diabetic Retinopathy Severity Prediction
by: Jyostna Devi Bodapati, et al.
Published: (2020-05-01) -
The clash between two worlds in human action recognition: supervised feature training vs Recurrent ConvNet
by: Raptis, Konstantinos
Published: (2017) -
Service Action Recognition in Power Supply Business Hall with 3D-Fused ConvNet
by: Tongyao Lin, et al.
Published: (2021-01-01)