Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.13091/1008
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Muhammad, Khan | - |
dc.contributor.author | Mustaqeem | - |
dc.contributor.author | Ullah, Amin | - |
dc.contributor.author | Imran, Ali Shariq | - |
dc.contributor.author | Sajjad, Muhammad | - |
dc.contributor.author | Kıran, Mustafa Servet | - |
dc.contributor.author | de Albuquerque, Victor Hugo C. | - |
dc.date.accessioned | 2021-12-13T10:32:19Z | - |
dc.date.available | 2021-12-13T10:32:19Z | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 0167-739X | - |
dc.identifier.issn | 1872-7115 | - |
dc.identifier.uri | https://doi.org/10.1016/j.future.2021.06.045 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.13091/1008 | - |
dc.description.abstract | Human action recognition in videos is an active area of research in computer vision and pattern recognition. Nowadays, artificial intelligence (AI) based systems are needed for human-behavior assessment and security purposes. The existing action recognition techniques are mainly using pre-trained weights of different AI architectures for the visual representation of video frames in the training stage, which affect the features' discrepancy determination, such as the distinction between the visual and temporal signs. To address this issue, we propose a bi-directional long short-term memory (BiLSTM) based attention mechanism with a dilated convolutional neural network (DCNN) that selectively focuses on effective features in the input frame to recognize the different human actions in the videos. In this diverse network, we use the DCNN layers to extract the salient discriminative features by using the residual blocks to upgrade the features that keep more information than a shallow layer. Furthermore, we feed these features into a BiLSTM to learn the long-term dependencies, which is followed by the attention mechanism to boost the performance and extract the additional high-level selective action related patterns and cues. We further use the center loss with Softmax to improve the loss function that achieves a higher performance in the video-based action classification. The proposed system is evaluated on three benchmarks, i.e., UCF11, UCF sports, and J-HMDB datasets for which it achieved a recognition rate of 98.3%, 99.1%, and 80.2%, respectively, showing 1%-3% improvement compared to the state-of-the-art (SOTA) methods. (C) 2021 Elsevier B.V. All rights reserved. | en_US |
dc.description.sponsorship | ERCIM 'Alain Benoussan' Fellowship Programme [2019-40]; Brazilian National Council for Research and Development (CNPq)Conselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPQ) [304315/2017-6, 430274/2018-1] | en_US |
dc.description.sponsorship | This work was carried out during the tenure of an ERCIM 'Alain Benoussan' Fellowship Programme under the Contract 2019-40, Color and Visual Computing Lab at the Department of Computer Science, NTNU, Gjovik, Norway. The work of Victor Hugo C. de Albuquerque was supported in part by the Brazilian National Council for Research and Development (CNPq) under Grant 304315/2017-6 and Grant 430274/2018-1. | en_US |
dc.language.iso | en | en_US |
dc.publisher | ELSEVIER | en_US |
dc.relation.ispartof | FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | Artificial Intelligence | en_US |
dc.subject | Action Recognition | en_US |
dc.subject | Attention Mechanism | en_US |
dc.subject | Big Data | en_US |
dc.subject | Dilated Convolutional Neural Network | en_US |
dc.subject | Deep Bi-Directional Lstm | en_US |
dc.subject | Multimedia Data Security | en_US |
dc.subject | Big Data | en_US |
dc.subject | Framework | en_US |
dc.subject | Security | en_US |
dc.subject | Internet | en_US |
dc.subject | Machine | en_US |
dc.subject | Fusion | en_US |
dc.subject | System | en_US |
dc.subject | Things | en_US |
dc.title | Human action recognition using attention based LSTM network with dilated CNN features | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1016/j.future.2021.06.045 | - |
dc.identifier.scopus | 2-s2.0-85111316846 | en_US |
dc.department | Fakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü | en_US |
dc.authorid | Muhammad, Khan/0000-0003-4055-7412 | - |
dc.authorwosid | Muhammad, Khan/L-9059-2016 | - |
dc.authorwosid | , Mustaqeem/AAM-9396-2020 | - |
dc.authorwosid | de Albuquerque, Victor Hugo C./C-3677-2016 | - |
dc.authorwosid | Ullah, Amin/AAH-5034-2020 | - |
dc.authorwosid | Sannino, Giovanna/N-1319-2013 | - |
dc.identifier.volume | 125 | en_US |
dc.identifier.startpage | 820 | en_US |
dc.identifier.endpage | 830 | en_US |
dc.identifier.wos | WOS:000687315100009 | en_US |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.authorscopusid | 56651946700 | - |
dc.authorscopusid | 57212930354 | - |
dc.authorscopusid | 57195399776 | - |
dc.authorscopusid | 56109077100 | - |
dc.authorscopusid | 57215455402 | - |
dc.authorscopusid | 54403096500 | - |
dc.authorscopusid | 36239105500 | - |
dc.identifier.scopusquality | Q2 | - |
item.languageiso639-1 | en | - |
item.fulltext | With Fulltext | - |
item.cerifentitytype | Publications | - |
item.openairetype | Article | - |
item.grantfulltext | embargo_20300101 | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
crisitem.author.dept | 02.03. Department of Computer Engineering | - |
Appears in Collections: | Mühendislik ve Doğa Bilimleri Fakültesi Koleksiyonu Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collections WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collections |
Files in This Item:
File | Size | Format | |
---|---|---|---|
1-s2.0-S0167739X21002405-main.pdf Until 2030-01-01 | 2.39 MB | Adobe PDF | View/Open Request a copy |
CORE Recommender
SCOPUSTM
Citations
22
checked on Apr 20, 2024
WEB OF SCIENCETM
Citations
104
checked on Apr 20, 2024
Page view(s)
174
checked on Apr 22, 2024
Download(s)
6
checked on Apr 22, 2024
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.