Semi-CNN Architecture for Effective Spatio-Temporal Learning in Action Recognition
This paper introduces a fusion convolutional architecture for efficient learning of spatio-temporal features in video action recognition. Unlike 2D convolutional neural networks (CNNs), 3D CNNs can be applied directly on consecutive frames to extract spatio-temporal features. The aim of this work is...
Main Authors: | Mei Chee Leong, Dilip K. Prasad, Yong Tsui Lee, Feng Lin |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/2/557 |
Similar Items
-
Action Recognition Based on the Fusion of Graph Convolutional Networks with High Order Features
by: Jiuqing Dong, et al.
Published: (2020-02-01) -
Human Action Recognition Based on Selected Spatio-Temporal Features via Bidirectional LSTM
by: Wenhui Li, et al.
Published: (2018-01-01) -
Action Recognition Algorithm of Spatio–Temporal Differential LSTM Based on Feature Enhancement
by: Kai Hu, et al.
Published: (2021-08-01) -
Video Copy Detection Using Spatio-Temporal CNN Features
by: Zhili Zhou, et al.
Published: (2019-01-01) -
SAST: Learning Semantic Action-Aware Spatial-Temporal Features for Efficient Action Recognition
by: Fei Wang, et al.
Published: (2019-01-01)