Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Samir Al-Stouhi"'
Autor:
K. S. Chidanand Kumar, Samir Al-Stouhi
Publikováno v:
WACV (Workshops)
This paper explores efficient techniques to improve PolarNet model performance to address the real-time semantic segmentation of LiDAR point clouds. The core framework consists of an encoder network, Atrous spatial pyramid pooling (ASPP)/Dense Atrous
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1014f4ef58b2d83662065ee5f1cd881e
https://doi.org/10.1109/wacvw52041.2021.00017
https://doi.org/10.1109/wacvw52041.2021.00017
Autor:
Samir Al-Stouhi, K. Kumar
Publikováno v:
Proceedings of the 6th International Conference on Vehicle Technology and Intelligent Transport Systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::48b3db298db02bd30329674fe6f3829d
https://doi.org/10.5220/0009340000002550
https://doi.org/10.5220/0009340000002550
Autor:
K. S. Chidanand Kumar, Samir Al-Stouhi
Publikováno v:
VEHITS
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a7092450a735dd96b79de685f012d460
https://doi.org/10.5220/0009340004320439
https://doi.org/10.5220/0009340004320439
Autor:
Jimmy Chiu, Thang Lian, Lichao Ma, Jiawei Huang, Alexandre Miranda Anon, Samir Al-Stouhi, Akansel Cosgun, Mahmut Demir, Hasan Tafish
Publikováno v:
Intelligent Vehicles Symposium
Each year, millions of motor vehicle traffic accidents all over the world cause a large number of fatalities, injuries and significant material loss. Automated Driving (AD) has potential to drastically reduce such accidents. In this work, we focus on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::62ab7feb3fe413fd0948944139520a57
http://arxiv.org/abs/1705.01187
http://arxiv.org/abs/1705.01187
Autor:
Samir Al-Stouhi, Radovan Miucic
Publikováno v:
VTC Fall
Lane-level localization is the basis for successful deployment of Intelligent Transportation Systems. Global Navigation Satellite System can provide lane-level position in open (non-obstructed) environments. A new area of research aims for a collabor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40a21c858065a49160a80a447b3bbf28
https://doi.org/10.1109/vtcfall.2016.7880889
https://doi.org/10.1109/vtcfall.2016.7880889
Autor:
Chandan K. Reddy, Samir Al-Stouhi
Publikováno v:
Knowledge and information systems. 48(1)
A fundamental problem in data mining is to effectively build robust classifiers in the presence of skewed data distributions. Class imbalance classifiers are trained specifically for skewed distribution datasets. Existing methods assume an ample supp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4191e5da72f1e8c425a6f0d8e974897b
https://pubmed.ncbi.nlm.nih.gov/27378821
https://pubmed.ncbi.nlm.nih.gov/27378821
Autor:
Sichao Yang, Samir Al-Stouhi, James A Misener, Wai-hoi Chan, Sue Bai, Radovan Miucic, Xinzhou Wu
Publikováno v:
VTC Fall
The prevalence of smartphones presents a unique opportunity to develop a system that can have a significant impact on reducing the annual 400,000 fatalities from pedestrian traffic accidents. This system gives 360 degrees, extended range, NLOS view w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33e5697ed8eb7b050f6132f7c87ff1cf
https://doi.org/10.1109/vtcfall.2014.6965898
https://doi.org/10.1109/vtcfall.2014.6965898
Autor:
Chandan K. Reddy, Samir Al-Stouhi
Publikováno v:
SDM
Researchers have attempted to improve the quality of clustering solutions through various mechanisms. A promising new approach to improve clustering quality is to combine data from multiple related datasets (tasks) and apply multi-task clustering. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bcecfd7834451be71dd188f76f1aac46
https://doi.org/10.1137/1.9781611973440.90
https://doi.org/10.1137/1.9781611973440.90
Publikováno v:
ICTAI
Small datasets pose a tremendous challenge in machine learning due to the few available training examples compounded with the relative rarity of certain labels which can potentially impede the development of a representative hypothesis. We define ``R
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1ecf65714bd27b0ff43995eef68fd339
https://doi.org/10.1109/ictai.2012.103
https://doi.org/10.1109/ictai.2012.103
Autor:
Chandan K. Reddy, Samir Al-Stouhi
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783642237799
ECML/PKDD (1)
ECML/PKDD (1)
Instance-based transfer learning methods utilize labeled examples from one domain to improve learning performance in another domain via knowledge transfer. Boosting-based transfer learning algorithms are a subset of such methods and have been applied
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::24f4df58652ffc9aa9d7ef28a92d6c51
https://doi.org/10.1007/978-3-642-23780-5_14
https://doi.org/10.1007/978-3-642-23780-5_14