Zobrazeno 1 - 10
of 127
pro vyhledávání: '"Luc Claesen"'
Publikováno v:
Frontiers in Neurorobotics, Vol 16 (2022)
Obtaining accurate depth information is key to robot grasping tasks. However, for transparent objects, RGB-D cameras have difficulty perceiving them owing to the objects' refraction and reflection properties. This property makes it difficult for huma
Externí odkaz:
https://doaj.org/article/c522ac9fa9074ece8ae280be4d8f6c98
Autor:
Kai Huang, Bowen Li, Dongliang Xiong, Haitian Jiang, Xiaowen Jiang, Xiaolang Yan, Luc Claesen, Dehong Liu, Junjian Chen, Zhili Liu
Publikováno v:
ACM Transactions on Design Automation of Electronic Systems. 28:1-24
Deep Neural Networks (DNNs) have achieved remarkable success in various Artificial Intelligence applications. Quantization is a critical step in DNNs compression and acceleration for deployment. To further boost DNN execution efficiency, many works e
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::447b379872d63fcf7fc1256b86758a6a
https://doi.org/10.1145/3549535
https://doi.org/10.1145/3549535
Autor:
Kai Huang, Bowen Li, Siang Chen, Luc Claesen, Wei Xi, Junjian Chen, Xiaowen Jiang, Zhili Liu, Dongliang Xiong, Xiaolang Yan
Publikováno v:
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 42:190-203
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3cd67946319f2503c34cf4ef2400649c
https://doi.org/10.1109/tcad.2022.3168506
https://doi.org/10.1109/tcad.2022.3168506
Autor:
Guibiao Fang, Junhong Chen, Dayong Liang, Muhammad Asim, Frank Van Reeth, Luc Claesen, Zhenguo Yang, Wenyin Liu
Publikováno v:
Neural Processing Letters.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4c75fa0360bc4f2d95ccb30ab8566bf4
https://doi.org/10.1007/s11063-023-11273-6
https://doi.org/10.1007/s11063-023-11273-6
Autor:
Xiaowen Jiang, Bowen Li, Dongliang Xiong, Luc Claesen, Kai Huang, Junjian Chen, Siang Chen, Zhili Liu, Hao Yao
Publikováno v:
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 41:1902-1915
Deep Neural Networks have achieved remarkable advancement in various intelligence tasks. However, the massive computation and storage consumption limit applications on resource-constrained devices. While channel pruning has been widely applied to com
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::42f6db899361262faebca176585da9cd
https://doi.org/10.1109/tcad.2021.3093835
https://doi.org/10.1109/tcad.2021.3093835
Publikováno v:
Expert Review of Medical Devices. 18:47-62
Background: Research proves that the apprenticeship model, which is the gold standard for training surgical residents, is obsolete. For that reason, there is a continuing effort toward the developm...
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de255c02b7004757e40f41dc14592adf
https://doi.org/10.1080/17434440.2021.1860750
https://doi.org/10.1080/17434440.2021.1860750
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 29:1179-1193
Depth image-based rendering (DIBR) techniques have recently drawn more attention in various 3D applications. In this paper, a real-time high-quality DIBR system that consists of disparity estimation and view synthesis is proposed. For disparity estim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::79b1e5749a39bf4e78416aa6e5cbc484
https://doi.org/10.1109/tcsvt.2018.2825022
https://doi.org/10.1109/tcsvt.2018.2825022
Publikováno v:
SIU
6 DoF position and orientation estimation is vital for many real-time applications. It is essential to meet low latency, high accuracy and reliability requirements, especially when used for real-time haptic feedback calculation in medical application
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92f1eb237d0cf4d422643919c2452259
https://doi.org/10.1109/siu49456.2020.9302192
https://doi.org/10.1109/siu49456.2020.9302192
Publikováno v:
Neural networks : the official journal of the International Neural Network Society. 130
Activated hidden units in convolutional neural networks (CNNs), known as feature maps, dominate image representation, which is compact and discriminative. For ultra-large datasets, high dimensional feature maps in float format not only result in high
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::94dcba085937446578b2114540df9e5c
https://pubmed.ncbi.nlm.nih.gov/32589586
https://pubmed.ncbi.nlm.nih.gov/32589586
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030670696
ECCV Workshops (3)
ECCV Workshops (3)
In recent years, remarkable progress has been made in single image super-resolution due to the powerful representation capabilities of deep neural networks. However, the superior performance is at the expense of excessive computation costs, limiting
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::532295e182d5893937dc002e2392e734
https://doi.org/10.1007/978-3-030-67070-2_7
https://doi.org/10.1007/978-3-030-67070-2_7
