Zobrazeno 1 - 10
of 23
pro vyhledávání: '"M Shujah Islam"'
Publikováno v:
Applied Sciences, Vol 13, Iss 9, p 5437 (2023)
Recent years have seen an explosion in interest in and development of action recognition based on skeletal data. Contemporary methods using fully gated units can successfully extract characteristics from human skeletons by relying on the human topolo
Externí odkaz:
https://doaj.org/article/74ff2de8adc24f30a981ef14fbc48f26
Publikováno v:
Signal, Image and Video Processing. 17:1677-1685
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9e307c16af92f6f63f2249a4184e344f
https://doi.org/10.1007/s11760-022-02378-x
https://doi.org/10.1007/s11760-022-02378-x
Publikováno v:
Journal of Intelligent & Fuzzy Systems. 43:7351-7362
The method of marking video clips with action symbols is known as vision-based human activity recognition. Robust solutions to this problem have a variety of practical implementations. Due to differences in motion performance, recording environments,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::44e5151b246b498837f30f89f7ea643a
https://doi.org/10.3233/jifs-213514
https://doi.org/10.3233/jifs-213514
Publikováno v:
Journal of Intelligent & Fuzzy Systems. 43:159-170
Caption generation using an encoder-decoder approach has recently been extensively studied and implemented in various domains, including image captioning and code captioning. In this research article, we propose one particular approach for completing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::621e36d7fb2331e6410100a79c9db380
https://doi.org/10.3233/jifs-211907
https://doi.org/10.3233/jifs-211907
Publikováno v:
Neural Processing Letters. 54:1481-1494
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b71237d0b9bb92d1b7145e8f2b82261f
https://doi.org/10.1007/s11063-021-10585-9
https://doi.org/10.1007/s11063-021-10585-9
Publikováno v:
Multimedia Tools and Applications. 81:29955-29975
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::115e859b13ad9a948af3914b56e6c8c2
https://doi.org/10.1007/s11042-022-12291-7
https://doi.org/10.1007/s11042-022-12291-7
Publikováno v:
Multimedia Tools and Applications. 81:681-694
Human pose estimation methods have difficulties predicting the correct pose for persons due to challenges in scale variation. Existing works in this domain mainly focus on single-person pose estimation. To counter this challenge we have developed a s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::575f7599d148589360b42668723edbc3
https://doi.org/10.1007/s11042-021-11374-1
https://doi.org/10.1007/s11042-021-11374-1
Autor:
Aliya Tabassum Abbasi, Rashid Khan, Md. Shohidul Islam, M. Shujah Islam, Zhongfu Ye, Md. Imran Hossain, Nuzhat Naqvi, Rizwan Ullah
Publikováno v:
Circuits, Systems, and Signal Processing. 40:4651-4685
Security and privacy have been continuously compromised in the modern multimedia network by various signal processing attacks. As a result, digital data owners are losing copyright protection, data security, and content authentication. A secure and r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::418e537af8d8c572018583ce595603db
https://doi.org/10.1007/s00034-021-01690-0
https://doi.org/10.1007/s00034-021-01690-0
Publikováno v:
Applied Intelligence. 51:6001-6013
Human action recognition is still an uncertain computer vision problem, which could be solved by a robust action descriptor. As a solution, we proposed an action recognition descriptor using only the 3D skeleton joint’s points to perform this unset
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2f8237be3f413b3bdb31941cd6c03d07
https://doi.org/10.1007/s10489-020-02176-3
https://doi.org/10.1007/s10489-020-02176-3
Autor:
Shamsa Kanwal, Nuzhat Naqvi, M. Shujah Islam, Khush Bakhat, M. Mattah Islam, Zhongfu Ye, Mansoor Iqbal
Publikováno v:
IET Image Processing. 14:417-422
This study introduces an action descriptor that has the ability to perform human action recognition efficiently for one and two person(s). The authors' proposed descriptor computes information like motion, spatial-temporal, diversion with respect to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e25d556866d2f64aa5576ee3bae847be
https://doi.org/10.1049/iet-ipr.2018.6437
https://doi.org/10.1049/iet-ipr.2018.6437