Zobrazeno 1 - 10
of 12
pro vyhledávání: '"Jihan Yang"'
Autor:
Xi Rao, Jihan Yang, Zilin Chen, Yidie Yuan, Qiubing Chen, Xue Feng, Lizhao Qin, Yongping Zhang
Publikováno v:
Bioactive Materials, Vol 5, Iss 2, Pp 192-200 (2020)
Diamond like carbon (DLC) films with different C–C sp2/sp3 ratios were prepared by tuning the N2 flow rate in a filtered cathodic vacuum arc (FCVA) system. The increase of N2 flow rate facilitated the increase of C–C sp2/sp3 ratio (1.09–2.66),
Externí odkaz:
https://doaj.org/article/63946f3c333f41a4b9067aea7fc37936
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence.
In this paper, we present a self-training method, named ST3D++, with a holistic pseudo label denoising pipeline for unsupervised domain adaptation on 3D object detection. ST3D++ aims at reducing noise in pseudo label generation as well as alleviating
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c538777af1a7f0c6927fd380d29a20ad
https://pubmed.ncbi.nlm.nih.gov/36279352
https://pubmed.ncbi.nlm.nih.gov/36279352
Autor:
Yidie Yuan, Yongping Zhang, Jihan Yang, Xi Rao, Lizhao Qin, Qiubing Chen, Xue Feng, Zilin Chen
Publikováno v:
Bioactive Materials, Vol 5, Iss 2, Pp 192-200 (2020)
Bioactive Materials
Bioactive Materials
Diamond like carbon (DLC) films with different C–C sp2/sp3 ratios were prepared by tuning the N2 flow rate in a filtered cathodic vacuum arc (FCVA) system. The increase of N2 flow rate facilitated the increase of C–C sp2/sp3 ratio (1.09–2.66),
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1528f04a4e843d27278e194f43185f68
http://www.sciencedirect.com/science/article/pii/S2452199X20300219
http://www.sciencedirect.com/science/article/pii/S2452199X20300219
Publikováno v:
CVPR
We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D detector on the source domain with our proposed random object scaling strateg
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::783ac6f91e2c798df490ae4bd2ef932d
http://arxiv.org/abs/2103.05346
http://arxiv.org/abs/2103.05346
While self-training has advanced semi-supervised semantic segmentation, it severely suffers from the long-tailed class distribution on real-world semantic segmentation datasets that make the pseudo-labeled data bias toward majority classes. In this p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53ee05e3ff8f36d3052a785d677b6eac
Autor:
Yongping Zhang, Jihan Yang
Publikováno v:
Advances in Materials Physics and Chemistry. :157-176
Due to its unique properties such as high hardness, light transmittance, thermal conductance, chemical stability and corrosion resistance, diamond has drawn tremendous attention in last two decades. These specific properties made diamond film a promi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a39d24d52f9d8b26cb870b8122445b86
https://doi.org/10.4236/ampc.2018.84011
https://doi.org/10.4236/ampc.2018.84011
Publikováno v:
ICCV
Domain adaptation enables the learner to safely generalize into novel environments by mitigating domain shifts across distributions. Previous works may not effectively uncover the underlying reasons that would lead to the drastic model degradation on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::28684254ade4c1c0a382608d2d4982be
https://doi.org/10.1109/iccv.2019.00151
https://doi.org/10.1109/iccv.2019.00151
Publikováno v:
AAAI
We focus on Unsupervised Domain Adaptation (UDA) for the task of semantic segmentation. Recently, adversarial alignment has been widely adopted to match the marginal distribution of feature representations across two domains globally. However, this s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2394f843d245060dbc1ab4e218ab3948
Autor:
Yidie Yuan, Qunliang Song, Binglian Yong, Jihan Yang, Jing li, Tan Xiaodong, Chenglin Chu, Xue Feng, Rao Xi, Zilin Chen
Publikováno v:
Journal of the mechanical behavior of biomedical materials. 88
In the present work, a new type of porous Ti-based alloy scaffold with high porosity (about 75%) and interconnected pores in the range of 300–1000 µm was fabricated by polymeric foam replication method with TiNbZr powders. This porous scaffold, wh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::326e2c15e1843aece897e89b43a956b2
https://pubmed.ncbi.nlm.nih.gov/30196185
https://pubmed.ncbi.nlm.nih.gov/30196185
Publikováno v:
Materials Research Express. 5:095403
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::59ff1791c63ff9a900e59812533d515f
https://doi.org/10.1088/2053-1591/aad8e3
https://doi.org/10.1088/2053-1591/aad8e3