Action Recognition in Videos Using Pre-Trained 2D Convolutional Neural Networks

Action Recognition in Videos Using Pre-Trained 2D Convolutional Neural Networks

A pre-trained 2D CNN (Convolutional Neural Network) can be used for the spatial stream in the two-stream CNN structure for videos, treating the representative frame selected from the video as an input. However, the CNN for the temporal stream in the two-stream CNN needs training from scratch using t...

Full description

Bibliographic Details
Main Authors: Jun-Hwa Kim, Chee Sun Won
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Convolutional neural network (CNN)
action recognition
video analysis
two-stream convolutional neural networks
Online Access:https://ieeexplore.ieee.org/document/9047853/

Internet

https://ieeexplore.ieee.org/document/9047853/

Similar Items