Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Guan, Jiazhi"'
Autor:
Guan, Jiazhi, Yang, Quanwei, Wang, Kaisiyuan, Zhou, Hang, He, Shengyi, Xu, Zhiliang, Feng, Haocheng, Ding, Errui, Wang, Jingdong, Xie, Hongtao, Zhao, Youjian, Liu, Ziwei
Recently, 2D speaking avatars have increasingly participated in everyday scenarios due to the fast development of facial animation techniques. However, most existing works neglect the explicit control of human bodies. In this paper, we propose to dri
Externí odkaz:
http://arxiv.org/abs/2410.10696
Autor:
Guan, Jiazhi, Xu, Zhiliang, Zhou, Hang, Wang, Kaisiyuan, He, Shengyi, Zhang, Zhanwang, Liang, Borong, Feng, Haocheng, Ding, Errui, Liu, Jingtuo, Wang, Jingdong, Zhao, Youjian, Liu, Ziwei
Lip-syncing videos with given audio is the foundation for various applications including the creation of virtual presenters or performers. While recent studies explore high-fidelity lip-sync with different techniques, their task-orientated models eit
Externí odkaz:
http://arxiv.org/abs/2408.03284
Autor:
Guan, Jiazhi, Hu, Tianshu, Zhou, Hang, Guo, Zhizhi, Deng, Lirui, Quan, Chengbin, Ding, Errui, Zhao, Youjian
The issue of detecting deepfakes has garnered significant attention in the research community, with the goal of identifying facial manipulations for abuse prevention. Although recent studies have focused on developing generalized models that can dete
Externí odkaz:
http://arxiv.org/abs/2305.12881
Autor:
Guan, Jiazhi, Zhang, Zhanwang, Zhou, Hang, Hu, Tianshu, Wang, Kaisiyuan, He, Dongliang, Feng, Haocheng, Liu, Jingtuo, Ding, Errui, Liu, Ziwei, Wang, Jingdong
Despite recent advances in syncing lip movements with any audio waves, current methods still struggle to balance generation quality and the model's generalization ability. Previous studies either require long-term data for training or produce a simil
Externí odkaz:
http://arxiv.org/abs/2305.05445
Despite encouraging progress in deepfake detection, generalization to unseen forgery types remains a significant challenge due to the limited forgery clues explored during training. In contrast, we notice a common phenomenon in deepfake: fake video c
Externí odkaz:
http://arxiv.org/abs/2207.10402
Autor:
Guan, Jiazhi, Zhou, Hang, Hong, Zhibin, Ding, Errui, Wang, Jingdong, Quan, Chengbin, Zhao, Youjian
Recent advances in face forgery techniques produce nearly visually untraceable deepfake videos, which could be leveraged with malicious intentions. As a result, researchers have been devoted to deepfake detection. Previous studies have identified the
Externí odkaz:
http://arxiv.org/abs/2207.02803
Autor:
Hughes, ChristopherR. (AUTHOR)
Publikováno v:
Japan Forum. Jul2008, Vol. 20 Issue 2, p245-266. 22p.
Autor:
Hughes, Christopher R. (AUTHOR)
Publikováno v:
Journal of Contemporary China. May2005, Vol. 14 Issue 43, p247-267. 21p.
This open access book constitutes the refereed proceedings of the 18th China Annual Conference on Cyber Security, CNCERT 2022, held in Beijing, China, in August 2022. The 17 papers presented were carefully reviewed and selected from 64 submissions.
Autor:
John Wong, Yongnian Zheng
In the spring of 1992, Deng Xiaoping made a historical tour of south China, popularly known as the Nanxun (”southern tour”). During the tour, he boldly called for more radical economic reform and further opening up of China. The Nanxun has become