Zobrazeno 1 - 10
of 1 687
pro vyhledávání: '"Zhang Weijia"'
Autor:
Liu Liang, Zhang Hao, Zhang Chaonan, Chen Jinbiao, Zhang Baoji, Bai Xiangen, Song Shengyao, Chen Qian, Zhang Weijia
Publikováno v:
Brodogradnja, Vol 75, Iss 3, Pp 1-22 (2024)
In order to investigate the impact of marine propeller wake fields on sediment siltation in shallow water channels, this study employs the unsteady RANS approach and the Volume of Fluid model. A full-scale numerical self-propulsion test was conducted
Externí odkaz:
https://doaj.org/article/26a995414c5f45de9871b521a5fb3ee8
Autor:
Yin Lu, Li Minghui, Liu Lizhe, Sun Chenhua, Wang Dongdong, Wang Ke, Lin Wenliang, Zhang Weijia, Wei Pengxiao, Cai Wei, Liu Hao, Deng Yaohua
Publikováno v:
Electronics Letters, Vol 59, Iss 8, Pp n/a-n/a (2023)
Abstract In this letter, a novel digital pre‐distortion (DPD) scheme for an end‐to‐end forward link (FL) channel in a satellite internet network (SIN) is first proposed. It aims at the unprecedented challenge of the model of non‐stationary (N
Externí odkaz:
https://doaj.org/article/4a4e3f1739654e75ac5a958a3202e4ff
Spatio-temporal forecasting is a critical component of various smart city applications, such as transportation optimization, energy management, and socio-economic analysis. Recently, several automated spatio-temporal forecasting methods have been pro
Externí odkaz:
http://arxiv.org/abs/2409.16586
Few-shot point cloud 3D object detection (FS3D) aims to identify and localise objects of novel classes from point clouds, using knowledge learnt from annotated base classes and novel classes with very few annotations. Thus far, this challenging task
Externí odkaz:
http://arxiv.org/abs/2408.17036
Multi-instance partial-label learning (MIPL) addresses scenarios where each training sample is represented as a multi-instance bag associated with a candidate label set containing one true label and several false positives. Existing MIPL algorithms h
Externí odkaz:
http://arxiv.org/abs/2408.14369
Autor:
Zhang, Weijia, Aliannejadi, Mohammad, Pei, Jiahuan, Yuan, Yifei, Huang, Jia-Hong, Kanoulas, Evangelos
Large language models (LLMs) often generate content with unsupported or unverifiable content, known as "hallucinations." To address this, retrieval-augmented LLMs are employed to include citations in their content, grounding the content in verifiable
Externí odkaz:
http://arxiv.org/abs/2408.12398
Autor:
Zhang, Weijia, Huang, Jia-Hong, Vakulenko, Svitlana, Xu, Yumo, Rajapakse, Thilina, Kanoulas, Evangelos
Query-focused summarization (QFS) is a fundamental task in natural language processing with broad applications, including search engines and report generation. However, traditional approaches assume the availability of relevant documents, which may n
Externí odkaz:
http://arxiv.org/abs/2408.10357
Although attention-based multi-instance learning algorithms have achieved impressive performances on slide-level whole slide image (WSI) classification tasks, they are prone to mistakenly focus on irrelevant patterns such as staining conditions and t
Externí odkaz:
http://arxiv.org/abs/2408.09449
Pre-trained Language Models (PLMs), such as ChatGPT, have significantly advanced the field of natural language processing. This progress has inspired a series of innovative studies that explore the adaptation of PLMs to time series analysis, intendin
Externí odkaz:
http://arxiv.org/abs/2408.08328
Autor:
Xu Qianwei, Zhang Weijia
Publikováno v:
e-Polymers, Vol 21, Iss 1, Pp 166-178 (2021)
The cationic-π/π–π interaction existing between the surface of CNTs and the imidazole ring of ILs benefited the dispersion of CNTs in the TPU.
Externí odkaz:
https://doaj.org/article/08fcceafed664c9cacc8e2c2d9a93ea7