Zobrazeno 1 - 10
of 137
pro vyhledávání: '"Li, Yangxi"'
Deep neural networks are vulnerable to backdoor attacks. Among the existing backdoor defense methods, trigger reverse engineering based approaches, which reconstruct the backdoor triggers via optimizations, are the most versatile and effective ones c
Externí odkaz:
http://arxiv.org/abs/2404.12852
Autor:
Wu, Wei, Zhang, Jian-Wei, Li, Yangxi, Huang, Ke, Chen, Rui-Min, Maimaiti, Mireguli, Luo, Jing-Si, Chen, Shao-Ke, Wu, Di, Zhu, Min, Wang, Chun-Lin, Su, Zhe, Liang, Yan, Yao, Hui, Wei, Hai-Yan, Zheng, Rong-Xiu, Du, Hong-Wei, Luo, Fei-Hong, Li, Pin, Wang, Ergang, Polychronakos, Constantin, Fu, Jun-Fen
Publikováno v:
In The Lancet Regional Health - Western Pacific November 2024 52
Autor:
Zhao, Yanan, Jing, Liwei, Ma, Xin, Li, Yangxi, Zhang, Jing, Li, Chenyang, Liu, Guangtian, Dai, Jiaqi, Cao, Shengxuan
Publikováno v:
In Journal of Tissue Viability November 2024 33(4):550-560
Publikováno v:
In Separation and Purification Technology 19 February 2025 354 Part 4
Publikováno v:
In Separation and Purification Technology 2 July 2024 339
Autor:
Cui, Cheng, Ye, Zhi, Li, Yangxi, Li, Xinjian, Yang, Min, Wei, Kai, Dai, Bing, Zhao, Yanmei, Liu, Zhongji, Pang, Rong
Simi-Supervised Recognition Challenge-FGVC7 is a challenging fine-grained recognition competition. One of the difficulties of this competition is how to use unlabeled data. We adopted pseudo-tag data mining to increase the amount of training data. Th
Externí odkaz:
http://arxiv.org/abs/2006.10702
Autor:
Cai, Hengyi, Chen, Hongshen, Zhang, Cheng, Song, Yonghao, Zhao, Xiaofang, Li, Yangxi, Duan, Dongsheng, Yin, Dawei
Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of human conversations, the complexity of training dialogues varies greatly.
Externí odkaz:
http://arxiv.org/abs/2003.00639
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
User identity linkage is a task of recognizing the identities of the same user across different social networks (SN). Previous works tackle this problem via estimating the pairwise similarity between identities from different SN, predicting the label
Externí odkaz:
http://arxiv.org/abs/1910.14273