A transfer learning-based efficient spatiotemporal human action recognition framework for long and overlapping action classes

Deep learning base solutions for computer vision made life easier for humans. Video data contain a lot of hidden information and patterns, that can be used for Human Action Recognition (HAR). HAR can apply to many areas, such as behavior analysis, intelligent video surveillance, and robotic vision....

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	The Journal of supercomputing Jg. 78; H. 2; S. 2873 - 2908
Hauptverfasser:	Bilal, Muhammad, Maqsood, Muazzam, Yasmin, Sadaf, Hasan, Najam Ul, Rho, Seungmin
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York Springer US 01.02.2022 Springer Nature B.V
Schlagworte:	Artificial Intelligence based Deep Video Data Analytics Compilers Computer Science Computer vision Data transmission Deep learning Feature extraction Human activity recognition Human motion Interpreters Iterative methods Machine learning Machine vision Occlusion Processor Architectures Programming Languages Surveillance Video data Human action recognition Transfer learning Overlapping actions Video content analysis Deep autoencoder
ISSN:	0920-8542, 1573-0484
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!