Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Jamonnak, Suphanut"'
Existing semantic segmentation approaches are often limited by costly pixel-wise annotations and predefined classes. In this work, we present CLIP-S$^4$ that leverages self-supervised pixel representation learning and vision-language models to enable
Externí odkaz:
http://arxiv.org/abs/2305.01040
Autor:
JAMONNAK, SUPHANUT
Geo-encoded visual information (images and videos) offers the potential to acquire fine-scale, multi-time period and associated contextualized data for a variety of geographical environments, especially when combined with additional insights and geo-
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics, 2021
Vision-based deep learning (DL) methods have made great progress in learning autonomous driving models from large-scale crowd-sourced video datasets. They are trained to predict instantaneous driving behaviors from video data captured by on-vehicle c
Externí odkaz:
http://arxiv.org/abs/2109.10895
Autor:
Ye, Xinyue1,2,3,4,5 xinyue.ye@gmail.com, Jamonnak, Suphanut3, Van Zandt, Shannon1, Newman, Galen1,3, Suermann, Patrick6
Publikováno v:
Frontiers of Urban & Rural Planning. 4/7/2024, Vol. 2 Issue 1, p1-13. 13p.
Publikováno v:
IEEE Transactions on Visualization & Computer Graphics 2020
Existing interactive visualization tools for deep learning are mostly applied to the training, debugging, and refinement of neural network models working on natural images. However, visual analytics tools are lacking for the specific application of x
Externí odkaz:
http://arxiv.org/abs/2009.02256
Autor:
Amiruzzaman, Md, Jamonnak, Suphanut
Publikováno v:
2020 6th Conference on Data Science and Machine Learning Applications (CDMA)
This paper presents a new application for multi-dimensional Skyline query. The idea presented in this paper can be used to find best shopping malls based on users requirements. A web-based application was used to simulate the problem and proposed sol
Externí odkaz:
http://arxiv.org/abs/2003.08215
This extended abstract presents a visualization system, which is designed for domain scientists to visually understand their deep learning model of extracting multiple attributes in x-ray scattering images. The system focuses on studying the model be
Externí odkaz:
http://arxiv.org/abs/1910.04357
Autor:
Jamonnak, Suphanut
Mobile devices are rapidly becoming the new medium of educational and social life for young people, and mobile educational games have become an important mechanism for learning. To enhance plant science learning, we developed a mobile educational gam
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Huang, Xinyi1 (AUTHOR), Jamonnak, Suphanut1 (AUTHOR), Zhao, Ye1 (AUTHOR), Wu, Tsung Heng1 (AUTHOR), Xu, Wei2 (AUTHOR)
Publikováno v:
Computer Graphics Forum. Jun2021, Vol. 40 Issue 3, p227-238. 12p. 6 Diagrams, 2 Charts.