Zobrazeno 1 - 10
of 15
pro vyhledávání: '"HAOTAO WANG"'
Publikováno v:
Applied Sciences, Vol 13, Iss 21, p 11961 (2023)
SiCp/Al composites are used in the aerospace, automotive, and electronics fields, among others, due to their excellent physical and mechanical properties. However, as they are hard-to-machine materials, poor surface quality has become a major limitat
Externí odkaz:
https://doaj.org/article/29493d13ecf14588bbb184546f73cad7
Publikováno v:
Micromachines, Vol 14, Iss 7, p 1350 (2023)
Ultrasonic-assisted grinding (UAG) is widely used in the manufacture of hard and brittle materials. However, the process removal mechanism was never elucidated and its potential is yet to be fully exploited. In this paper, the mechanism of material r
Externí odkaz:
https://doaj.org/article/6a7efaedecac4055baccd37878863623
Autor:
SINA MOHSENI1 smohseni@nvidia.com, HAOTAO WANG2 htwang@utexas.edu, CHAOWEI XIAO3 atlaswang@utexas.edu, ZHIDING YU1 zhidingy@nvidia.com, ZHANGYANG WANG2 chaoweix@nvidia.com, JAY YADAWA1 jyadawa@nvidia.com
Publikováno v:
ACM Computing Surveys. Aug2023, Vol. 55 Issue 8, p1-38. 38p.
Publikováno v:
Micromachines; Volume 14; Issue 7; Pages: 1350
Ultrasonic-assisted grinding (UAG) is widely used in the manufacture of hard and brittle materials. However, the process removal mechanism was never elucidated and its potential is yet to be fully exploited. In this paper, the mechanism of material r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=multidiscipl::3b7c076dc733586a69198b78f5e2a727
Autor:
Duc Hoang, Haotao Wang, Handong Zhao, Ryan Rossi, Sungchul Kim, Kanak Mahadik, Zhangyang Wang
Publikováno v:
Proceedings of the 31st ACM International Conference on Information & Knowledge Management.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d2a227a17305544b36724eb3937dc3cf
https://doi.org/10.1145/3511808.3557242
https://doi.org/10.1145/3511808.3557242
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:7702-7710
Protecting privacy in gradient-based learning has become increasingly critical as more sensitive information is being used. Many existing solutions seek to protect the sensitive gradients by constraining the overall privacy cost within a constant bud
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d258dfc1c57be28b8a3a02777d37b279
https://doi.org/10.1609/aaai.v35i9.16941
https://doi.org/10.1609/aaai.v35i9.16941
The open-world deployment of Machine Learning (ML) algorithms in safety-critical applications such as autonomous vehicles needs to address a variety of ML vulnerabilities such as interpretability, verifiability, and performance limitations. Research
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::41d24bdb3f7e731b10882a43c36a64ab
http://arxiv.org/abs/2106.04823
http://arxiv.org/abs/2106.04823
Publikováno v:
CVPR
Recently, the group maximum differentiation competition (gMAD) has been used to improve blind image quality assessment (BIQA) models, with the help of full-reference metrics. When applying this type of approach to troubleshoot "best-performing" BIQA
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a716da410a2b8a4a2304c8e998c3254
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 44(4)
We investigate privacy-preserving, video-based action recognition in deep learning, a problem with growing importance in smart camera applications. A novel adversarial training framework is formulated to learn an anonymization transform for input vid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::54f2b2689718b3771876644062a615d5
https://pubmed.ncbi.nlm.nih.gov/32986544
https://pubmed.ncbi.nlm.nih.gov/32986544