HARNet in deep learning approach—a systematic survey

A comprehensive examination of human action recognition (HAR) methodologies situated at the convergence of deep learning and computer vision is the subject of this article. We examine the progression from handcrafted feature-based approaches to end-to-end learning, with a particular focus on the sig...

Full description

Saved in:
Bibliographic Details
Published inScientific reports Vol. 14; no. 1; pp. 8363 - 15
Main Authors Kumar, Neelam Sanjeev, Deepika, G., Goutham, V., Buvaneswari, B., Reddy, R. Vijaya Kumar, Angadi, Sanjeevkumar, Dhanamjayulu, C., Chinthaginjala, Ravikumar, Mohammad, Faruq, Khan, Baseem
Format Journal Article
LanguageEnglish
Published London Nature Publishing Group UK 10.04.2024
Nature Publishing Group
Nature Portfolio
Subjects
639/166
639/4077
Accuracy
Automation
CNN
Computer engineering
Computer science
Computer vision
Datasets
Deep learning
Feature-based approaches
Human action recognition (HAR)
Humanities and Social Sciences
Machine learning
multidisciplinary
Neural networks
Research methodology
Science
Science (multidisciplinary)
Sensors
Surveys
Taxonomy
Trends
Human action recognition (HAR)
Deep learning
CNN
Accuracy
Feature-based approaches
Online AccessGet full text
ISSN2045-2322
2045-2322
DOI10.1038/s41598-024-58074-y

Cover

More Information
Summary:A comprehensive examination of human action recognition (HAR) methodologies situated at the convergence of deep learning and computer vision is the subject of this article. We examine the progression from handcrafted feature-based approaches to end-to-end learning, with a particular focus on the significance of large-scale datasets. By classifying research paradigms, such as temporal modelling and spatial features, our proposed taxonomy illuminates the merits and drawbacks of each. We specifically present HARNet, an architecture for Multi-Model Deep Learning that integrates recurrent and convolutional neural networks while utilizing attention mechanisms to improve accuracy and robustness. The VideoMAE v2 method ( https://github.com/OpenGVLab/VideoMAEv2 ) has been utilized as a case study to illustrate practical implementations and obstacles. For researchers and practitioners interested in gaining a comprehensive understanding of the most recent advancements in HAR as they relate to computer vision and deep learning, this survey is an invaluable resource.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-024-58074-y