Zobrazeno 1 - 10
of 106
pro vyhledávání: '"Sun, Yankui"'
Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of vision-language tasks.
Externí odkaz:
http://arxiv.org/abs/2308.16689
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Applied Surface Science 1 January 2022 571
With the introduction of spectral-domain optical coherence tomography (SDOCT), much larger image datasets are routinely acquired compared to what was possible using the previous generation of time-domain OCT. Thus, there is a critical need for the de
Externí odkaz:
http://arxiv.org/abs/1508.00966
Publikováno v:
In Surface & Coatings Technology 15 November 2020 401
Autor:
Qiu, Jiaming, Sun, Yankui
Publikováno v:
In Computers in Biology and Medicine August 2019 111
Rapid fabrication of superhydrophobic high-silicon aluminum alloy surfaces with corrosion resistance
Autor:
Sun, Yankui, Zhao, Danyang, Song, Jinlong, Wang, Cong, Zhang, Zhihao, Huang, Liu, Liu, Jiyu, Liu, Ziai
Publikováno v:
In Results in Physics March 2019 12:1082-1088
We present a second iteration of a machine learning approach to static code analysis and fingerprinting for weaknesses related to security, software engineering, and others using the open-source MARF framework and the MARFCAT application based on it
Externí odkaz:
http://arxiv.org/abs/1207.3718
Autor:
Mokhov, Serguei A., Sun, Yankui
We overview the existing OCT work, especially the practical aspects of it. We create a novel algorithm for 3D OCT segmentation with the goals of speed and/or accuracy while remaining flexible in the design and implementation for future extensions and
Externí odkaz:
http://arxiv.org/abs/1204.6725
Autor:
Sun, Yankui, Zhang, Tian
Publikováno v:
China Patent Application (201110247341.5), 2011
With the introduction of spectral-domain optical coherence tomography (OCT), much larger image datasets are routinely acquired compared to what was possible using the previous generation of time-domain OCT. Thus, the need for 3-D segmentation methods
Externí odkaz:
http://arxiv.org/abs/1204.6385