Zobrazeno 1 - 10
of 84
pro vyhledávání: '"Liu, Yaofang"'
Autor:
Liu, Yang, Liu, Yaofang, Pan, Jinshan, Hui, Yuxiang, Jia, Fan, Chan, Raymond H., Zeng, Tieyong
Most existing super-resolution methods and datasets have been developed to improve the image quality in well-lighted conditions. However, these methods do not work well in real-world low-light conditions as the images captured in such conditions lose
Externí odkaz:
http://arxiv.org/abs/2410.12961
Autor:
Liu, Yaofang, Ren, Yumeng, Cun, Xiaodong, Artola, Aitor, Liu, Yang, Zeng, Tieyong, Chan, Raymond H., Morel, Jean-michel
Diffusion models have revolutionized image generation, and their extension to video generation has shown promise. However, current video diffusion models~(VDMs) rely on a scalar timestep variable applied at the clip level, which limits their ability
Externí odkaz:
http://arxiv.org/abs/2410.03160
Video restoration task aims to recover high-quality videos from low-quality observations. This contains various important sub-tasks, such as video denoising, deblurring and low-light enhancement, since video often faces different types of degradation
Externí odkaz:
http://arxiv.org/abs/2401.14754
Autor:
Chen, Haoxin, Xia, Menghan, He, Yingqing, Zhang, Yong, Cun, Xiaodong, Yang, Shaoshu, Xing, Jinbo, Liu, Yaofang, Chen, Qifeng, Wang, Xintao, Weng, Chao, Shan, Ying
Video generation has increasingly gained interest in both academia and industry. Although commercial tools can generate plausible videos, there is a limited number of open-source models available for researchers and engineers. In this work, we introd
Externí odkaz:
http://arxiv.org/abs/2310.19512
Autor:
Liu, Yaofang, Cun, Xiaodong, Liu, Xuebo, Wang, Xintao, Zhang, Yong, Chen, Haoxin, Liu, Yang, Zeng, Tieyong, Chan, Raymond, Shan, Ying
The vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services have been developed to generate high-quality videos. However, these methods often use a few
Externí odkaz:
http://arxiv.org/abs/2310.11440
Autor:
Pan, Fei, Wu, Yutong, Cui, Kangning, Chen, Shuxun, Li, Yanfang, Liu, Yaofang, Shakoor, Adnan, Zhao, Han, Lu, Beijia, Zhi, Shaohua, Chan, Raymond, Sun, Dong
Despite recent advances in data-independent and deep-learning algorithms, unstained live adherent cell instance segmentation remains a long-standing challenge in cell image processing. Adherent cells' inherent visual characteristics, such as low cont
Externí odkaz:
http://arxiv.org/abs/2301.11499
Autor:
Liu, Yaofang, Zhang, Xinyue, Wan, Wenlong, Liu, Shaoyu, Liu, Yingdi, Liu, Hu, Zeng, Xueying, Zhang, Qing
Coronary angiography is the "gold standard" for diagnosing coronary artery disease (CAD). At present, the methods for detecting and evaluating coronary artery stenosis cannot satisfy the clinical needs, e.g., there is no prior study of detecting sten
Externí odkaz:
http://arxiv.org/abs/2112.06149
Autor:
Pan, Fei, Wu, Yutong, Cui, Kangning, Chen, Shuxun, Li, Yanfang, Liu, Yaofang, Shakoor, Adnan, Zhao, Han, Lu, Beijia, Zhi, Shaohua, Chan, Raymond Hon-Fu, Sun, Dong
Publikováno v:
In Computers in Biology and Medicine November 2024 182
Publikováno v:
陆军军医大学学报, Vol 45, Iss 4, Pp 335-342 (2023)
Objective To investigate the distribution of human papillomavirus (HPV) subtypes in women with different age and analyze the relationship between HPV and cervical lesions. Methods A cross-sectional study was conducted on 4 084 patients who underwent
Externí odkaz:
https://doaj.org/article/20388a9cb16a40588e182cd760cd3d53
Publikováno v:
International Journal of Gynecology & Obstetrics; Aug2024, Vol. 166 Issue 2, p502-511, 10p