Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Sheikh Faisal Rashid"'
Autor:
Shehzad Afzal, Sohaib Ghani, Mohamad Mazen Hittawe, Sheikh Faisal Rashid, Omar M. Knio, Markus Hadwiger, Ibrahim Hoteit
Publikováno v:
ACM Transactions on Interactive Intelligent Systems. 13:1-41
Image and video data analysis has become an increasingly important research area with applications in different domains such as security surveillance, healthcare, augmented and virtual reality, video and image editing, activity analysis and recogniti
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2b34ba905bf5e55d01608b7d244e3092
https://doi.org/10.1145/3576935
https://doi.org/10.1145/3576935
Publikováno v:
Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f0a6010dc6a4588631170c6a39e482f7
https://doi.org/10.1145/3573942.3573968
https://doi.org/10.1145/3573942.3573968
Autor:
Riaz Ahmad, Muhammad Zeshan Afzal, Saeeda Naz, Andreas Dengel, Marcus Liwicki, Sheikh Faisal Rashid
Publikováno v:
The International Arab Journal of Information Technology. 17:299-305
This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e.,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::70cdd677e1619990c37d7911a3ed9ffc
https://doi.org/10.34028/iajit/17/3/3
https://doi.org/10.34028/iajit/17/3/3
Publikováno v:
2022 2nd International Conference on Artificial Intelligence (ICAI).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4db02afbb1d247c0871d6eb0c9783396
https://doi.org/10.1109/icai55435.2022.9773637
https://doi.org/10.1109/icai55435.2022.9773637
Publikováno v:
2022 4th International Conference on Natural Language Processing (ICNLP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::252010b7de0be32df8a37397f6805431
https://doi.org/10.1109/icnlp55136.2022.00044
https://doi.org/10.1109/icnlp55136.2022.00044
Autor:
Schultze, Frank C, Zully Ritter, Rühlicke, Stefan, Schmucker, Michael, Reiswich, Andreas, Esslinger, Katrin, Pischek-Koch, Kerstin, Wache, Stefanie, Dietrich, Michael, Sheikh Faisal Rashid, Kesztyüs, Tibor, Haag, Martin, Schirrmeister, Wiebke, Krefting, Dagmar, Blaschke, Sabine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f1d180290433f278beda538f35fd1a6c
Publikováno v:
2021 4th International Conference on Artificial Intelligence and Pattern Recognition.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3ca24c3b4e5c2f67e9f62512a80e52cc
https://doi.org/10.1145/3488933.3489001
https://doi.org/10.1145/3488933.3489001
Graph convolution network with node feature optimization using cross attention for few-shot learning
Publikováno v:
Proceedings of the 2nd ACM International Conference on Multimedia in Asia.
Graph convolution network (GCN) is an important method recently developed for few-shot learning. The adjacency matrix in GCN models is constructed based on graph node features to represent the graph node relationships, according to which, the graph n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f76188d7f5eb63a501e4476ed6f21c8e
https://doi.org/10.1145/3444685.3446278
https://doi.org/10.1145/3444685.3446278
Autor:
Yu Hao, Fuping Wang, Sheikh Faisal Rashid, Telecommunications, Xi’an, China, Ying Liu, Yangge Qiao
Publikováno v:
Journal of Image and Graphics. 9
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df649092c34034c4ef0bedd8f7da2676
https://doi.org/10.18178/joig.9.3.74-86
https://doi.org/10.18178/joig.9.3.74-86
Publikováno v:
ICDAR
Tables are an easy way to represent information in a structural form. Table recognition is important for the extraction of such information from document images. Usually, modern OCR systems provide textual information coming from tables without recog
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ac8c17d6b7d30216ff9cc6f11593042
https://doi.org/10.1109/icdar.2017.132
https://doi.org/10.1109/icdar.2017.132