Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Hyung Jin Chang"'
Publikováno v:
IEEE Access, Vol 11, Pp 32051-32060 (2023)
Quantization is an effective technique to reduce the memory and computational complexity of CNNs. Recent advances utilize additive powers-of-two to perform non-uniform quantization, which resembles a normal distribution and shows better performance t
Externí odkaz:
https://doaj.org/article/b0236e1cd13f419aaa3e79c7256e1265
Publikováno v:
IEEE Access, Vol 9, Pp 79562-79571 (2021)
We propose a self-supervised visual learning method by predicting the variable playback speeds of a video. Without semantic labels, we learn the spatio-temporal visual representation of the video by leveraging the variations in the visual appearance
Externí odkaz:
https://doaj.org/article/230dea68582a43df9ce724bdf7da3764
Publikováno v:
IEEE Access, Vol 8, Pp 45700-45714 (2020)
Assistive robots in home environments are steadily increasing in popularity. Due to significant variabilities in human behaviour, as well as physical characteristics and individual preferences, personalising assistance poses a challenging problem. In
Externí odkaz:
https://doaj.org/article/3fa3087859904f1cb3ec42503e8eb8b9
Publikováno v:
Proceedings of the ACM on Human-Computer Interaction. 7:1-19
We propose a new gaze-initialised optimisation framework to generate aesthetically pleasing image crops based on user description. We extended the existing description-based image cropping dataset by collecting user eye movements corresponding to the
Autor:
Jaeho Shin, Kyungjin Kim, Kyeonghee Han, Jeong Min In, Hyung-Jin Chang, Sojung Shim, Siwoo Kim
Publikováno v:
International Journal of Automotive Technology. 23:1483-1490
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031250842
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6aea9963672683f4ea2a926fa09c2f27
https://doi.org/10.1007/978-3-031-25085-9_7
https://doi.org/10.1007/978-3-031-25085-9_7
Autor:
Daniel Rueckert, Xi Jia, Linlin Shen, Alexander Thorley, Wei Chen, Huaqi Qiu, Antonio de Marvao, Jinming Duan, Iain B. Styles, Ales Leonardis, Declan P. O'Regan, Hyung Jin Chang
Publikováno v:
IEEE Transactions on Medical Imaging. 41:199-212
Data-driven deep learning approaches to image registration can be less accurate than conventional iterative approaches, especially when training data is limited. To address this whilst retaining the fast inference speed of deep learning, we propose V
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:792-800
In this paper, we propose a normative approach to modeling apparently human irrational decision making (cognitive biases) that makes use of inherently rational computational mechanisms. We view preferential choice tasks as sequential decision making
Autor:
Linfang Zheng, Ales Leonardis, Tze Ho Elden Tse, Nora Horanyi, Hua Chen, Wei Zhang, Hyung Jin Chang
Publikováno v:
2022 International Conference on Robotics and Automation (ICRA).