Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Huaxin Xi"'
Publikováno v:
Complex & Intelligent Systems, Vol 10, Iss 3, Pp 3213-3233 (2024)
Abstract Deep neural networks are vulnerable to adversarial attacks, bringing high risk to numerous security-critical applications. Existing adversarial defense algorithms primarily concentrate on optimizing adversarial training strategies to improve
Externí odkaz:
https://doaj.org/article/5b872562bf584fb18c3dfc524f595a35
Autor:
Samuel O. Adeosun, Cuicui Ge, Qiao Niu, Kaihong He, Jeremy W. Duncan, Hai-yang Wang, Qinli Zhang, Huaxin Xi, Huiting Peng
Publikováno v:
Journal of Applied Toxicology. 37:1053-1064
Although nanomaterials have the potential to improve human life, their sideline effects on human health seem to be inevitable and still are unknown. Some studies have investigated the genotoxicity of alumina nanoparticles (AlNPs); however, this effec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::05f8d1f3167e42b135a109e47172f91c
https://doi.org/10.1002/jat.3456
https://doi.org/10.1002/jat.3456
Autor:
Qinli, Zhang, Haiyang, Wang, Cuicui, Ge, Jeremy, Duncan, Kaihong, He, Samuel O, Adeosun, Huaxin, Xi, Huiting, Peng, Qiao, Niu
Publikováno v:
Journal of applied toxicology : JAT. 37(9)
Although nanomaterials have the potential to improve human life, their sideline effects on human health seem to be inevitable and still are unknown. Some studies have investigated the genotoxicity of alumina nanoparticles (AlNPs); however, this effec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::b22b4efbdd77060d030f0d8c9a9ac72f
https://pubmed.ncbi.nlm.nih.gov/28337774
https://pubmed.ncbi.nlm.nih.gov/28337774
Publikováno v:
EURASIP Journal on Image and Video Processing, Vol 2020, Iss 1, Pp 1-17 (2020)
Abstract Considering the significant progress made on RGB-based deep salient object detection (SOD) methods, this paper seeks to bridge the gap between those 2D methods and 4D light field data, instead of implementing specific 4D methods. We observe
Externí odkaz:
https://doaj.org/article/51a37e198bfe40c58bdc51b50a69b659
Publikováno v:
IEEE Access, Vol 8, Pp 63632-63642 (2020)
Person re-identification (Re-ID) has become a hot topic in both research and industry. We joined in a person Re-ID challenge of the First National Artificial Intelligence Challenge (China, 2019) and found some model designs and training tricks work g
Externí odkaz:
https://doaj.org/article/6d1a3cd658164098abc36ec2715b0b0e
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 13, Pp 2778-2792 (2020)
The class imbalance problem exists widely in vision data. In these imbalanced datasets, the majority classes dominate the loss and influence the gradient. Hence, these datasets have a significantly negative impact on the performance of many state-of-
Externí odkaz:
https://doaj.org/article/e80280ff1098445087732755026014e7