Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Yulei Niu"'
Publikováno v:
Energies, Vol 15, Iss 7, p 2421 (2022)
The purpose of this work is to investigate the effect of different initial temperatures on the combustion characteristics of RDX materials. In the experiments, the electric heating plate below the RDX samples was controlled so that the initial temper
Externí odkaz:
https://doaj.org/article/795cdb84b70942a79920b9bc0da37432
Autor:
Xingxuan Zhang, Yue He, Tan Wang, Jiaxin Qi, Han Yu, Zimu Wang, Jie Peng, Renzhe Xu, Zheyan Shen, Yulei Niu, Hanwang Zhang, Peng Cui
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031250743
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9dbff803f660bbb6cfe24670e0ca4e68
https://doi.org/10.1007/978-3-031-25075-0_29
https://doi.org/10.1007/978-3-031-25075-0_29
Publikováno v:
Journal of Energy Storage. 63:107017
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bc73e45278b03d3a98df9c83a1f6d559
https://doi.org/10.1016/j.est.2023.107017
https://doi.org/10.1016/j.est.2023.107017
Publikováno v:
Journal of Energy Engineering. 148
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9b9210c746af63672a1ed2bb9b60598a
https://doi.org/10.1061/(asce)ey.1943-7897.0000846
https://doi.org/10.1061/(asce)ey.1943-7897.0000846
Publikováno v:
Springer Proceedings in Physics ISBN: 9789811917738
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0f1f6fdc3de57863de01887aa745907a
https://doi.org/10.1007/978-981-19-1774-5_20
https://doi.org/10.1007/978-981-19-1774-5_20
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200588
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::10f0d83edd98d658ee5e3f75df3b6a6e
https://doi.org/10.1007/978-3-031-20059-5_7
https://doi.org/10.1007/978-3-031-20059-5_7
We address the overlooked unbiasedness in existing long-tailed classification methods: we find that their overall improvement is mostly attributed to the biased preference of tail over head, as the test distribution is assumed to be balanced; however
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1e140cc05290b1c312af806b41114e44
Publikováno v:
ACL/IJCNLP (1)
Pre-trained multilingual language models, e.g., multilingual-BERT, are widely used in cross-lingual tasks, yielding the state-of-the-art performance. However, such models suffer from a large performance gap between source and target languages, especi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd0634c4e8bf874d2b80164d4e656808
https://doi.org/10.18653/v1/2021.acl-long.48
https://doi.org/10.18653/v1/2021.acl-long.48
Publikováno v:
Computer Vision – ECCV 2020 Workshops ISBN: 9783030660956
ECCV Workshops (2)
ECCV Workshops (2)
Most existing action recognition models are large convolutional neural networks that work only with raw RGB frames as input. However, practical applications require lightweight models that directly process compressed videos. In this work, for the fir
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2533967433b9dfda915bbc9753bcb15
https://doi.org/10.1007/978-3-030-66096-3_24
https://doi.org/10.1007/978-3-030-66096-3_24
Publikováno v:
CVPR
Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e.g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach". Given such SGG, the down-stream tasks such as VQA c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c307f3df4130516b69407183df573940