Batch Entropy Supervised Convolutional Neural Networks for Feature Extraction and Harmonizing for Action Recognition

Batch Entropy Supervised Convolutional Neural Networks for Feature Extraction and Harmonizing for Action Recognition

Deep learning-based action recognition in videos has obtained much attention because of achieving remarkable performance in diverse applications. However, due to the heterogeneous background and noisy spatio-temporal cues, extracting highly discriminative features is still quite challenging. To deal...

Full description

Bibliographic Details
Main Authors: Md Imtiaz Hossain, Ashraf Siddique, Md Alamgir Hossain, Md Delowar Hossain, Eui-Nam Huh
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
BESS
HAFS
batch-entropy
augmentation
action recognition
feature fusion
Online Access:https://ieeexplore.ieee.org/document/9256204/

Internet

https://ieeexplore.ieee.org/document/9256204/

Similar Items