Zobrazeno 1 - 10
of 1 042
pro vyhledávání: '"Liang-Gee Chen"'
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2010 (2010)
Abandoned luggage represents a potential threat to public safety. Identifying objects as luggage, identifying the owners of such objects, and identifying whether owners have left luggage behind are the three main problems requiring solution. This pap
Externí odkaz:
https://doaj.org/article/07462118ccfe460487750b5fff0dca96
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 31:3679-3693
Belief propagation (BP)-based stereo matching has popular owing to its regularity and ability to yield promising results. Some commonly observed hardware-implementation challenges pertaining to the use of this algorithm are large memory requirements
Autor:
Liang-Gee Chen, Sih-Sian Wu
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 31:2981-2993
In this study, we propose a constant memory hardware architecture that can support weighted mode, median, and joint bilateral filters, which is referred to as CMWMF. This work aims to meet the high memory and computation requirements of processing de
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision (ICCV).
Publikováno v:
New Developments in Biomedical Engineering
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4e042ed378754e4fcbd3eb3c60c3ee37
http://www.intechopen.com/articles/show/title/design-and-implementation-of-leading-eigenvector-generator-for-on-chip-principal-component-analysis-
http://www.intechopen.com/articles/show/title/design-and-implementation-of-leading-eigenvector-generator-for-on-chip-principal-component-analysis-
Publikováno v:
ISCAS
CNN-based stereo matching methods achieve great performance but come with high computational requirements. Pruning a CNN can reduce the complexity but may in turn lead to memory conflicts, lowering throughput. Our proposed architecture and memory map
Publikováno v:
ISCAS
Sending local data to cloud servers is vulnerable to user privacy, and its long update latency. Meanwhile, the state-of- the-art stereo matching method is still computation demanding, fine-tuning the whole model on-device is not a practicable solutio
Publikováno v:
CVPR
Lossy image compression is often limited by the simplicity of the chosen loss measure. Recent research suggests that generative adversarial networks have the ability to overcome this limitation and serve as a multi-modal loss, especially for textures
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41591967c5a88b24520ddbf93f2049bc
http://arxiv.org/abs/2012.01874
http://arxiv.org/abs/2012.01874
Publikováno v:
IEEE Transactions on Image Processing. 26:603-618
Digital refocusing has a tradeoff between complexity and quality when using sparsely sampled light fields for low-storage applications. In this paper, we propose a fast physically correct refocusing algorithm to address this issue in a twofold way. F
Publikováno v:
ICCV
Scene Parsing is a crucial step to enable autonomous systems to understand and interact with their surroundings. Supervised deep learning methods have made great progress in solving scene parsing problems, however, come at the cost of laborious manua
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::107386c4189e40b88fb7b4aa749f69b7