Zobrazeno 1 - 10
of 2 055
pro vyhledávání: '"Xia Kun"'
Autor:
WANG Yu, WANG Suyue, JIN Ping, ZHU Yulong, XIA Kun, SUN Dandan, AI Wenlong, FU Xiaoming, YE Qunrong, LI Kai, WANG Xun
Publikováno v:
罕见病研究, Vol 1, Iss 2, Pp 189-195 (2022)
O'Sullivan-Mcleod syndrome is a very rare variant of MND with a good prognosis. Its clinical feature is distal lower motor neuron syndrome of both upper limbs, and there is no effective treatment at present. We reported a case of O'Sullivan-Mcleod sy
Externí odkaz:
https://doaj.org/article/c671e78f7f3a406381c04feae16daa42
Publikováno v:
IEEE Trans. on Artificial Intelligence, 5(7):3431-3444, 2024
Semi-supervised domain adaptation (SSDA) aims at training a high-performance model for a target domain using few labeled target data, many unlabeled target data, and plenty of auxiliary data from a source domain. Previous works in SSDA mainly focused
Externí odkaz:
http://arxiv.org/abs/2412.03212
Autor:
Xia Kun
Publikováno v:
SHS Web of Conferences, Vol 162, p 01013 (2023)
Bamboo flute is a traditional Chinese instrument. In the long history of China, the performance of bamboo flute has been used to express and transmit emotions, enriching the spiritual world of the Chinese people. Nowadays, with the continuous progres
Externí odkaz:
https://doaj.org/article/97cee0b05c64496eb602638c9ed68b9c
Temporal sentence grounding is a challenging task that aims to localize the moment spans relevant to a language description. Although recent DETR-based models have achieved notable progress by leveraging multiple learnable moment queries, they suffer
Externí odkaz:
http://arxiv.org/abs/2406.00143
Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to making ambiguo
Externí odkaz:
http://arxiv.org/abs/2404.16416
The crux of semi-supervised temporal action localization (SS-TAL) lies in excavating valuable information from abundant unlabeled videos. However, current approaches predominantly focus on building models that are robust to the error-prone target cla
Externí odkaz:
http://arxiv.org/abs/2403.11189
The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e.g., context and background, in an untrimmed video. While prior approaches have achieved substantial progress through devis
Externí odkaz:
http://arxiv.org/abs/2206.11493
Publikováno v:
In Ocean Engineering 15 December 2024 314 Part 1
Publikováno v:
Journal of Tropical Meteorology. Sep2024, Vol. 30 Issue 3, p241-256. 16p.
Autor:
Chen, Zhuohui, Wang, Xiang, Teng, Ziwei, Huang, Jing, Mo, Jianzhong, Qu, Chunrun, Wu, Yinghua, Liu, Zhixiong, Liu, Fangkun, Xia, Kun
Publikováno v:
In eBioMedicine September 2024 107