Optimizing Spatiotemporal Feature Learning in 3D Convolutional Neural Networks With Pooling Blocks

Optimizing Spatiotemporal Feature Learning in 3D Convolutional Neural Networks With Pooling Blocks

Image data contain spatial information only, thus making two-dimensional (2D) Convolutional Neural Networks (CNN) ideal for solving image classification problems. On the other hand, video data contain both spatial and temporal information that must be simultaneously analyzed to solve action recognit...

Full description

Bibliographic Details
Main Authors: Rockson Agyeman, Muhammad Rafiq, Hyun Kwang Shin, Bernhard Rinner, Gyu Sang Choi
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Action recognition
convolutional neural network
optimization
Online Access:https://ieeexplore.ieee.org/document/9425533/

Internet

https://ieeexplore.ieee.org/document/9425533/

Similar Items