Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Zeng, Xianhan"'
Autor:
Gao, Yiming, Liu, Feiyu, Wang, Liang, Lian, Zhenjie, Wang, Weixuan, Li, Siqin, Wang, Xianliang, Zeng, Xianhan, Wang, Rundong, Wang, Jiawei, Fu, Qiang, Yang, Wei, Huang, Lanxiao, Liu, Wei
MOBA games, e.g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far. However, these AI systems mainly focus on how to compete wit
Externí odkaz:
http://arxiv.org/abs/2304.11632
Deep learning has achieved enormous success in various industrial applications. Companies do not want their valuable data to be stolen by malicious employees to train pirated models. Nor do they wish the data analyzed by the competitors after using t
Externí odkaz:
http://arxiv.org/abs/2112.14420
The existing image embedding networks are basically vulnerable to malicious attacks such as JPEG compression and noise adding, not applicable for real-world copyright protection tasks. To solve this problem, we introduce a generative deep network bas
Externí odkaz:
http://arxiv.org/abs/2110.05689
Autor:
Wang, Ning, Zeng, Xianhan, Xie, Renjie, Gao, Zefei, Zheng, Yi, Liao, Ziran, Yang, Junyan, Wang, Qiao
Street architectures play an essential role in city image and streetscape analysing. However, existing approaches are all supervised which require costly labeled data. To solve this, we propose a street architectural unsupervised classification frame
Externí odkaz:
http://arxiv.org/abs/1905.12844