Výsledky vyhledávání

Akademický článek

Shoe-Print Image Retrieval With Multi-Part Weighted CNN

Autor: Zhanyu Ma, Yifeng Ding, Shaoguo Wen, Jiyang Xie, Yifeng Jin, Zhongwei Si, Haining Wang

Publikováno v: IEEE Access, Vol 7, Pp 59728-59736 (2019)

Identifying shoe-print impressions in the scene of crime (SoC) from database images is a challenging problem in forensic science due to the complicated impressing surface, the partial absence of on-site impressions, and the huge domain gap between th

Externí odkaz: https://doaj.org/article/c33ea1c1adb44999a8e534566779b9cf

Zobrazit plný text záznamu

Akademický článek

Influence of Cu on the Improvement of Magnetic Properties and Structure of L10 FePt Nanoparticles

Autor: Luran Zhang, Xinchen Du, Hongjie Lu, Dandan Gao, Huan Liu, Qilong Lin, Yongze Cao, Jiyang Xie, Wanbiao Hu

Publikováno v: Nanomaterials, Vol 11, Iss 5, p 1097 (2021)

L10 ordered FePt and FePtCu nanoparticles (NPs) with a good dispersion were successfully fabricated by a simple, green, one-step solid-phase reduction method. Fe (acac)3, Pt (acac)2, and CuO as the precursors were dispersed in NaCl and annealed at di

Externí odkaz: https://doaj.org/article/30d0722f6c794679a2cda2c165c86799

Zobrazit plný text záznamu

Akademický článek

Marked Enhancement of Roll-Off Frequency in FeCoN Synthetic Antiferromagnetic Films Deposited by Oblique Incidence

Autor: Luran Zhang, Dandan Gao, Huan Liu, Jiyang Xie, Wanbiao Hu

Publikováno v: Materials, Vol 12, Iss 14, p 2328 (2019)

A series of FeCoN films were successfully deposited on glass substrates in a magnetron sputtering system. Using oblique incidence method and FeCoN/Ru/FeCoN synthetic antiferromagnetic (SAF) structure, two additional anisotropies energy were introduce

Externí odkaz: https://doaj.org/article/76b7511f55e74c68a8b17b1e431429ec

Zobrazit plný text záznamu

Plný text ve formátu HTML

Report

Multi-head Uncertainty Inference for Adversarial Attack Detection

Autor: Yang, Yuqi, Yang, Songyun, Si, Jiyang Xie. Zhongwei, Guo, Kai, Zhang, Ke, Liang, Kongming

Deep neural networks (DNNs) are sensitive and susceptible to tiny perturbation by adversarial attacks which causes erroneous predictions. Various methods, including adversarial defense and uncertainty inference (UI), have been developed in recent yea

Externí odkaz: http://arxiv.org/abs/2212.10006

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání