Zobrazeno 1 - 10
of 1 008
pro vyhledávání: '"Liu Xuyang"'
Publikováno v:
Xibei zhiwu xuebao, Vol 44, Iss 2, Pp 205-218 (2024)
Abstract [Objective] Apocynum venetum L. is an important wild plant germplasm in China, which has important medicinal, ecological, and economic values. Although A . venetum is strong in salt tolerance, its wild population is gradually declining due
Externí odkaz:
https://doaj.org/article/1e1cba54934a474ca9ff00df572242ee
Autor:
Liao Jun, Yang Xianwu, Yang Jiejie, Xiao Jingjing, Liu Xuyang, Zhuo Yingquan, Yang Jiafei, Gu Huajian
Publikováno v:
Open Life Sciences, Vol 18, Iss 1, Pp e14-8 (2023)
This study aimed to investigate effects of pulmonary fractalkine (FKN/CX3CL1) on angiogenesis and tube formation. Tube forming capability of pulmonary vascular endothelial cells (PVECs) was evaluated. CCK-8 assay was used to evaluate proliferation of
Externí odkaz:
https://doaj.org/article/5c383976dc1b4814b7cca9cb7d2d37f7
Publikováno v:
Shanghai Jiaotong Daxue xuebao, Vol 57, Iss 3, Pp 253-263 (2023)
The electromagnetic induction leveling method has the characteristics of high efficiency and easy operation. It has a good application prospect in the thin plate leveling process. Based on the fixed inline coil induction leveling process used by the
Externí odkaz:
https://doaj.org/article/4f201e49ff0c4378ac7021d155886668
Publikováno v:
Nanotechnology Reviews, Vol 11, Iss 1, Pp 1386-1407 (2022)
In recent years, PVDF(polyvinylidene fluoride) and its copolymers have attracted great attention in the development of energy-harvesting devices because of their unique properties such as good flexibility, environmental friendliness, high halogen and
Externí odkaz:
https://doaj.org/article/d4616bfbef934dfe905d93dee472dbc3
Autor:
Wang, Shaobo, Tang, Hongxuan, Wang, Mingyang, Zhang, Hongrui, Liu, Xuyang, Li, Weiya, Hu, Xuming, Zhang, Linfeng
The debate between self-interpretable models and post-hoc explanations for black-box models is central to Explainable AI (XAI). Self-interpretable models, such as concept-based networks, offer insights by connecting decisions to human-understandable
Externí odkaz:
http://arxiv.org/abs/2410.21815
Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion transformers by cach
Externí odkaz:
http://arxiv.org/abs/2410.05317
Autor:
Liu, Xuyang, Liu, Ting, Huang, Siteng, Xin, Yi, Hu, Yue, Yin, Quanjun, Wang, Donglin, Chen, Honggang
Referring expression comprehension (REC) is a vision-language task to locate a target object in an image based on a language expression. Fully fine-tuning general-purpose pre-trained vision-language foundation models for REC yields impressive perform
Externí odkaz:
http://arxiv.org/abs/2407.01131
Autor:
Liu, Ting, Liu, Xuyang, Huang, Siteng, Shi, Liangtao, Xu, Zunnan, Xin, Yi, Yin, Quanjun, Liu, Xiaohong
Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-trained Vision Transformer (ViT) models to downstream applications. While current PEFT methods have achieved parameter efficiency, they overlook the efficiency
Externí odkaz:
http://arxiv.org/abs/2405.14700
With the advent of image super-resolution (SR) algorithms, how to evaluate the quality of generated SR images has become an urgent task. Although full-reference methods perform well in SR image quality assessment (SR-IQA), their reliance on high-reso
Externí odkaz:
http://arxiv.org/abs/2405.09472
Autor:
Liu, Ting, Liu, Xuyang, Huang, Siteng, Chen, Honggang, Yin, Quanjun, Qin, Long, Wang, Donglin, Hu, Yue
Visual grounding (VG) is a challenging task to localize an object in an image based on a textual description. Recent surge in the scale of VG models has substantially improved performance, but also introduced a significant burden on computational cos
Externí odkaz:
http://arxiv.org/abs/2405.06217