Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Muhammad Ferjad Naeem"'
Autor:
Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, A. Pagani, Didier Stricker, Muhammad Zeshan Afzal
Publikováno v:
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Compositional zero-shot learning aims to recognize unseen compositions of seen visual primitives of object classes and their states. While all primitives (states and objects) are observable during training in some combination, their complex interacti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::21d85bfb859c28b752f75ad547df00a1
https://hdl.handle.net/20.500.11850/593734
https://hdl.handle.net/20.500.11850/593734
Autor:
Syed Muhammad Kumail Raza, Faisal Shafait, Muhammad Mubasher Khan, Adnan Ul-Hasan, Noor ul Sehr Zia, Muhammad Ferjad Naeem
Publikováno v:
Neural Computing and Applications. 34:1635-1648
An offline handwriting recognition system for Urdu, a language with a user base of 200 Million and written in Nastaleeq script, has been a challenge for the research community. The key problems include recognition of complex ligature shapes and lack
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::076b3496360dcadfe6f490338dcf726b
https://doi.org/10.1007/s00521-021-06498-2
https://doi.org/10.1007/s00521-021-06498-2
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198144
Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be composable beyond the observed object classes. Towards this, we present 3D Compositional Zero-shot Learning as a proble
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c5096701ce69b1d1b7dc0617ee90b9d3
https://doi.org/10.1007/978-3-031-19815-1_41
https://doi.org/10.1007/978-3-031-19815-1_41
Compositional Zero-Shot learning (CZSL) aims to recognize unseen compositions of state and object visual primitives seen during training. A problem with standard CZSL is the assumption of knowing which unseen compositions will be available at test ti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::04087e106155e3e5397cadf181eb2f30
http://arxiv.org/abs/2105.01017
http://arxiv.org/abs/2105.01017
Publikováno v:
IEEE/CVF Conference on Computer Vision and Pattern Recognition
CVPR
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
CVPR
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) in the training set. This is challenging because the same state can for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fd8b0c2f6f65003f902aa419a856fdb2
https://hdl.handle.net/21.11116/0000-0009-84B1-921.11116/0000-0008-1542-6
https://hdl.handle.net/21.11116/0000-0009-84B1-921.11116/0000-0008-1542-6
Publikováno v:
ICDAR
A major hurdle in the development of practical Urdu Nastaleeq script OCR is the lack of transcribed data, which is a pre-requisite for training machine learning algorithms. Most of the previous research has focused on UPTI, a publicly available data
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ebdad7f124867fd7ad94a142e4a630ab
https://doi.org/10.1109/icdar.2017.30
https://doi.org/10.1109/icdar.2017.30
Autor:
Muhammad Ferjad Naeem
Publikováno v:
Aerospace Science and Technology. 13:27-35
Some in-service deterioration in any mechanical device, such as an aero-engine, is inevitable. Also in a country like Pakistan, there is a significant variation of day temperature over the year. As a result of experiencing deterioration (of the engin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::09e9f3a2d49ade232e77975b3d254367
https://doi.org/10.1016/j.ast.2008.02.004
https://doi.org/10.1016/j.ast.2008.02.004
Autor:
Muhammad Ferjad Naeem
Publikováno v:
Journal of Propulsion and Power. 24:624-628
H IGH-PERFORMANCE aircraft used in modern aviation, especially for military purposes, are complex in design and are required to operate under severe stresses and temperatures [1]. Thus, designer and users of these aircraft continually seek greater re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::008f36890f184e1c9e21ee864ae15e96
https://doi.org/10.2514/1.32019
https://doi.org/10.2514/1.32019
Autor:
Muhammad Ferjad Naeem
Publikováno v:
Applied Energy. 85:243-270
Some in-service deterioration in any mechanical device, such as an aircraft’s gas-turbine engine, is inevitable. However, its extent and rate depend upon the qualities of design and manufacture, as well as on the maintenance/repair practices follow
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b7f85f47938fbb37e821942b2ba92f33
https://doi.org/10.1016/j.apenergy.2007.02.011
https://doi.org/10.1016/j.apenergy.2007.02.011
Publikováno v:
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IEEE/CVF Conference on Computer Vision and Pattern Recognition
CVPR
IEEE/CVF Conference on Computer Vision and Pattern Recognition
CVPR
Compositional Zero-Shot learning (CZSL) requires to recognize state-object compositions unseen during training. In this work, instead of assuming prior knowledge about the unseen compositions, we operate in the open world setting, where the search sp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a39344aba79b6998d43839238d9a12e1