Zobrazeno 1 - 10
of 230
pro vyhledávání: '"TIAN, Jiayi"'
Autor:
Liu, Jiaheng, He, Tong, Yang, Honghui, Su, Rui, Tian, Jiayi, Wu, Junran, Guo, Hongcheng, Xu, Ke, Ouyang, Wanli
Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness. Besides, inevitable variations of different datasets make these methods become particularly sensitive t
Externí odkaz:
http://arxiv.org/abs/2211.09375
Pre-trained BERT models have achieved impressive accuracy on natural language processing (NLP) tasks. However, their excessive amount of parameters hinders them from efficient deployment on edge devices. Binarization of the BERT models can significan
Externí odkaz:
http://arxiv.org/abs/2210.15976
Autor:
Zhao, Yahao a, Ye, Furong a, Han, Changcun a, d, ⁎, Liu, Peng a, Liu, Wen a, Huang, Yizhong a, d, ⁎⁎, Chen, Xupeng a, Tian, Jiayi b, c, d, ⁎⁎⁎
Publikováno v:
In Ceramics International January 2025 51(1):940-948
Autor:
Yin, Lingshi, Nie, Xiuzhen, Deng, Guanying, Tian, Jiayi, Xiang, Ziyi, Abbasi, Sajjad, Chen, Haojie, Zhang, Wenping, Xiao, Ruihao, Gan, Chuneng, Zhang, You, Wen, Xiaofeng
Publikováno v:
In Journal of Hazardous Materials 5 December 2024 480
Publikováno v:
In Science of the Total Environment 1 December 2024 954
Autor:
Liang, Wenjing, Zhang, Wen, Tian, Jiayi, Zhang, Xinping, Lv, Xinyi, Qu, Ao, Chen, Jinyu, Wu, Zijian
Publikováno v:
In International Journal of Biological Macromolecules November 2024 281 Part 4
Autor:
Zhao, Yahao, Liu, Peng, Liu, Wen, Lv, Hui, Peng, Zhuo, Han, Changcun, Tian, Jiayi, Ye, Furong, Cheng, Zhengwang, Huang, Yizhong
Publikováno v:
In Separation and Purification Technology 19 February 2025 354 Part 3
Publikováno v:
In Engineering Applications of Artificial Intelligence July 2024 133 Part F
Publikováno v:
In Process Safety and Environmental Protection May 2024 185:492-510
Domain adaptation aims to leverage a label-rich domain (the source domain) to help model learning in a label-scarce domain (the target domain). Most domain adaptation methods require the co-existence of source and target domain samples to reduce the
Externí odkaz:
http://arxiv.org/abs/2103.14357