Zobrazeno 1 - 10
of 96
pro vyhledávání: '"Sheng-Jyh Wang"'
Autor:
Kuei-Tso Lee, Sheng-Jyh Wang
Publikováno v:
2022 IEEE Conference on Games (CoG).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::832d4ef814ba514a27040cf7f6f3705d
https://doi.org/10.1109/cog51982.2022.9893611
https://doi.org/10.1109/cog51982.2022.9893611
Publikováno v:
Journal of Advanced Agricultural Technologies. 6:180-186
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9f75b9f0e263400d460380a424af8e05
https://doi.org/10.18178/joaat.6.3.180-186
https://doi.org/10.18178/joaat.6.3.180-186
Publikováno v:
ISPACS
In this paper, we propose a patch-based contraction process for the improvement of image matting. Given an input image and a trimap, the proposed contraction process quickly refines the trimap by reclassifying the alpha values of the undetermined pix
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb4dbdf4eca501705f2d707d6ff64219
https://doi.org/10.1109/ispacs.2017.8266541
https://doi.org/10.1109/ispacs.2017.8266541
Publikováno v:
ICIP
The state-of-the-art models for semantic image segmentation usually contain a convolutional neural network (CNN) and a conditional random field (CRF). As a predictor, existing CNN techniques can generate a dense prediction result but may generate obv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1dbe3efff08ad0be5bd110b01b466784
https://doi.org/10.1109/icip.2017.8296488
https://doi.org/10.1109/icip.2017.8296488
Autor:
Sheng-Jyh Wang, Chen-Yu Tseng
Publikováno v:
IEEE Transactions on Image Processing. 23:4941-4953
Automatically extracting foreground objects from a natural image remains a challenging task. This paper presents a learning-based hierarchical graph for unsupervised matting. The proposed hierarchical framework progressively condenses image data from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6482851373f87d03bfb7907db388c9a4
https://doi.org/10.1109/tip.2014.2323132
https://doi.org/10.1109/tip.2014.2323132
Autor:
Chen-Yu Tseng, Sheng-Jyh Wang
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 24:2063-2076
This paper presents a maximum a posteriori (MAP) framework to incorporate a spatial consistency prior model for depth reconstruction in the shape-from-focus (SFF) process. Existing SFF techniques, which reconstruct a dense 3-D depth from multifocus i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b4f359b9f665da0ab31302cd0cea37a1
https://doi.org/10.1109/tcsvt.2014.2358873
https://doi.org/10.1109/tcsvt.2014.2358873
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 23:1598-1610
In this paper, we propose a vacant parking space detection system that operates day and night. In the daytime, the major challenges of the system include dramatic lighting variations, shadow effect, inter-object occlusion, and perspective distortion.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7d78c2daa15652877b7e01a5deacc531
https://doi.org/10.1109/tcsvt.2013.2254961
https://doi.org/10.1109/tcsvt.2013.2254961
Autor:
Sheng-Jyh Wang
Publikováno v:
2016 International Symposium on VLSI Design, Automation and Test (VLSI-DAT).
In this talk, we present an unsupervised hierarchical clustering method based on the split-and-merge scheme. In the splitting phase, we sequentially partition the feature space of the given data into smaller cells so that the probability distribution
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::098c3b25a1421fb2b25e1b8677282d2b
https://doi.org/10.1109/vlsi-dat.2016.7482564
https://doi.org/10.1109/vlsi-dat.2016.7482564
Autor:
Sheng-Jyh Wang, Tzu-Cheng Jen
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 22:831-843
In this paper, an efficient Bayesian framework is proposed for image contrast enhancement. Based on the image acquisition pipeline, we model the image enhancement problem as a maximum a posteriori (MAP) estimation problem, where the posteriori probab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::421a022c0445f00d910907ac7d7f5042
https://doi.org/10.1109/tcsvt.2011.2177184
https://doi.org/10.1109/tcsvt.2011.2177184
Autor:
Sheng-Jyh Wang, Ching-Chun Huang
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 20:1770-1785
In this paper, from the viewpoint of scene under standing, a three-layer Bayesian hierarchical framework (BHF) is proposed for robust vacant parking space detection. In practice, the challenges of vacant parking space inference come from dramatic lum
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a7b4cef860865e75af91b19e077e01d
https://doi.org/10.1109/tcsvt.2010.2087510
https://doi.org/10.1109/tcsvt.2010.2087510