Cargando…

A Comprehensive Review of Recent Deep Learning Techniques for Human Activity Recognition

Human action recognition is an important field in computer vision that has attracted remarkable attention from researchers. This survey aims to provide a comprehensive overview of recent human action recognition approaches based on deep learning using RGB video data. Our work divides recent deep lea...

Descripción completa

Detalles Bibliográficos
Autores principales: Le, Viet-Tuan, Tran-Trung, Kiet, Hoang, Vinh Truong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9045967/
https://www.ncbi.nlm.nih.gov/pubmed/35498187
http://dx.doi.org/10.1155/2022/8323962
_version_ 1784695421959929856
author Le, Viet-Tuan
Tran-Trung, Kiet
Hoang, Vinh Truong
author_facet Le, Viet-Tuan
Tran-Trung, Kiet
Hoang, Vinh Truong
author_sort Le, Viet-Tuan
collection PubMed
description Human action recognition is an important field in computer vision that has attracted remarkable attention from researchers. This survey aims to provide a comprehensive overview of recent human action recognition approaches based on deep learning using RGB video data. Our work divides recent deep learning-based methods into five different categories to provide a comprehensive overview for researchers who are interested in this field of computer vision. Moreover, a pure-transformer architecture (convolution-free) has outperformed its convolutional counterparts in many fields of computer vision recently. Our work also provides recent convolution-free-based methods which replaced convolution networks with the transformer networks that achieved state-of-the-art results on many human action recognition datasets. Firstly, we discuss proposed methods based on a 2D convolutional neural network. Then, methods based on a recurrent neural network which is used to capture motion information are discussed. 3D convolutional neural network-based methods are used in many recent approaches to capture both spatial and temporal information in videos. However, with long action videos, multistream approaches with different streams to encode different features are reviewed. We also compare the performance of recently proposed methods on four popular benchmark datasets. We review 26 benchmark datasets for human action recognition. Some potential research directions are discussed to conclude this survey.
format Online
Article
Text
id pubmed-9045967
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-90459672022-04-28 A Comprehensive Review of Recent Deep Learning Techniques for Human Activity Recognition Le, Viet-Tuan Tran-Trung, Kiet Hoang, Vinh Truong Comput Intell Neurosci Review Article Human action recognition is an important field in computer vision that has attracted remarkable attention from researchers. This survey aims to provide a comprehensive overview of recent human action recognition approaches based on deep learning using RGB video data. Our work divides recent deep learning-based methods into five different categories to provide a comprehensive overview for researchers who are interested in this field of computer vision. Moreover, a pure-transformer architecture (convolution-free) has outperformed its convolutional counterparts in many fields of computer vision recently. Our work also provides recent convolution-free-based methods which replaced convolution networks with the transformer networks that achieved state-of-the-art results on many human action recognition datasets. Firstly, we discuss proposed methods based on a 2D convolutional neural network. Then, methods based on a recurrent neural network which is used to capture motion information are discussed. 3D convolutional neural network-based methods are used in many recent approaches to capture both spatial and temporal information in videos. However, with long action videos, multistream approaches with different streams to encode different features are reviewed. We also compare the performance of recently proposed methods on four popular benchmark datasets. We review 26 benchmark datasets for human action recognition. Some potential research directions are discussed to conclude this survey. Hindawi 2022-04-20 /pmc/articles/PMC9045967/ /pubmed/35498187 http://dx.doi.org/10.1155/2022/8323962 Text en Copyright © 2022 Viet-Tuan Le et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Review Article
Le, Viet-Tuan
Tran-Trung, Kiet
Hoang, Vinh Truong
A Comprehensive Review of Recent Deep Learning Techniques for Human Activity Recognition
title A Comprehensive Review of Recent Deep Learning Techniques for Human Activity Recognition
title_full A Comprehensive Review of Recent Deep Learning Techniques for Human Activity Recognition
title_fullStr A Comprehensive Review of Recent Deep Learning Techniques for Human Activity Recognition
title_full_unstemmed A Comprehensive Review of Recent Deep Learning Techniques for Human Activity Recognition
title_short A Comprehensive Review of Recent Deep Learning Techniques for Human Activity Recognition
title_sort comprehensive review of recent deep learning techniques for human activity recognition
topic Review Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9045967/
https://www.ncbi.nlm.nih.gov/pubmed/35498187
http://dx.doi.org/10.1155/2022/8323962
work_keys_str_mv AT leviettuan acomprehensivereviewofrecentdeeplearningtechniquesforhumanactivityrecognition
AT trantrungkiet acomprehensivereviewofrecentdeeplearningtechniquesforhumanactivityrecognition
AT hoangvinhtruong acomprehensivereviewofrecentdeeplearningtechniquesforhumanactivityrecognition
AT leviettuan comprehensivereviewofrecentdeeplearningtechniquesforhumanactivityrecognition
AT trantrungkiet comprehensivereviewofrecentdeeplearningtechniquesforhumanactivityrecognition
AT hoangvinhtruong comprehensivereviewofrecentdeeplearningtechniquesforhumanactivityrecognition