Zobrazeno 1 - 10
of 394
pro vyhledávání: '"Luo, Sihui"'
Despite remarkable advancements, mainstream gaze estimation techniques, particularly appearance-based methods, often suffer from performance degradation in uncontrolled environments due to variations in illumination and individual facial attributes.
Externí odkaz:
http://arxiv.org/abs/2405.01439
Publikováno v:
In Journal of Advanced Research October 2024 64:213-221
Autor:
Zhang, Wenqiao, Shi, Haochen, Guo, Jiannan, Zhang, Shengyu, Cai, Qingpeng, Li, Juncheng, Luo, Sihui, Zhuang, Yueting
Publikováno v:
AAAI 2022
Text-based image captioning (TextCap) requires simultaneous comprehension of visual content and reading the text of images to generate a natural language description. Although a task can teach machines to understand the complex human environment furt
Externí odkaz:
http://arxiv.org/abs/2112.06558
Publikováno v:
Science China Information Sciences 62.8 (2019): 1-12
Human beings keep exploring the physical space using information means. Only recently, with the rapid development of information technologies and the increasing accumulation of data, human beings can learn more about the unknown world with data-drive
Externí odkaz:
http://arxiv.org/abs/2111.11872
Publikováno v:
In Journal of Visual Communication and Image Representation May 2024 101
Publikováno v:
In Magnetic Resonance Letters February 2024 4(1)
Knowledge distillation has demonstrated encouraging performances in deep model compression. Most existing approaches, however, require massive labeled data to accomplish the knowledge transfer, making the model compression a cumbersome and costly pro
Externí odkaz:
http://arxiv.org/abs/2012.04915
Publikováno v:
Chinese Journal of Magnetic Resonance, Vol 40, Iss 1, Pp 68-78 (2023)
Accelerating the release of the antenna residual energy to weaken the antenna ringing signal is beneficial to shorten the echo time (TE) of low-field nuclear magnetic resonance (NMR) instruments, thus improving the measurement resolution and signal-t
Externí odkaz:
https://doaj.org/article/3df286b40c7b4305b7287f84d6caebb1
Publikováno v:
In Journal of Visual Communication and Image Representation September 2023 95
An increasing number of well-trained deep networks have been released online by researchers and developers, enabling the community to reuse them in a plug-and-play way without accessing the training annotations. However, due to the large number of ne
Externí odkaz:
http://arxiv.org/abs/1906.10546