Visual intelligence for efficient human action recognition in human computers interaction applications
PLOS One · 05.03.2026 · 21 (3) · e0343132
DOI: 10.1371/journal.pone.0343132 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 05.03.2026. Verfasst von Noorah Alghasham und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia. Hauptthemen laut MEDLINE: Artificial Intelligence, User-Computer Interface, Pattern Recognition, Automated. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Human Action Recognition (HAR) is a pivotal area in computer vision, video surveillance, and human-computer interaction (HCI), driven by the need for efficient and accurate models to enhance HCI experiences. Traditional HAR methods often rely on hand-crafted features and shallow learning techniques, which limits their ability to capture complex patterns. In contrast, this study proposes an efficient HAR model that leverages deep neural networks, specifically a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), to enhance HCI through AI-powered action understanding. The model employs a pre-trained EfficientNetB7 network to extract rich spatial features from video frames, followed by a Long Short-Term Memory (LSTM) network to capture long-range temporal dependencies. This architecture enhances recognition accuracy while reducing computational complexity, making it highly suitable for HCI applications. Experimental results demonstrate the superior performance of the model, achieving a classification accuracy of 97.8% on the UCF101 dataset and 80.1% on the HMDB51 dataset, outperforming state-of-the-art HAR models. The proposed model eliminates the need for auxiliary assistive techniques like data augmentation, highlighting its efficiency and tremendous potential for real-world HCI applications that rely on accurate and efficient recognition of human actions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia.
ORCID-Profile: Waleed Albattah
Zitieren
APA
Alghasham, N., & Albattah, W. (2026). Visual intelligence for efficient human action recognition in human computers interaction applications. PLOS One, 21(3), e0343132. https://doi.org/10.1371/journal.pone.0343132
Vancouver
Alghasham N, Albattah W. Visual intelligence for efficient human action recognition in human computers interaction applications. PLOS One. 2026;21(3):e0343132. doi:10.1371/journal.pone.0343132
BibTeX
@article{Alghasham2026,
author = {Alghasham, Noorah and Albattah, Waleed},
title = {Visual intelligence for efficient human action recognition in human computers interaction applications},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {3},
pages = {e0343132},
doi = {10.1371/journal.pone.0343132}
}
EUVIMED